Search Results for author:
Found 339 papers, 140 papers with code
One-shot Face Sketch Synthesis in the Wild via Generative Diffusion Prior and Instruction Tuning
In this paper, we propose a one-shot face sketch synthesis method based on diffusion models.
SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks
Large Language Models (LLMs) are experiencing rapid advancements in complex reasoning, exhibiting remarkable generalization in mathematics and programming.
DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Transformer and Mamba
Recently, non-convolutional models such as the Vision Transformer (ViT) and Vision Mamba (Vim) have achieved remarkable performance in computer vision tasks.
MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models
Long Context Understanding (LCU) is a critical area for exploration in current large language models (LLMs).
UniErase: Unlearning Token as a Universal Erasure Primitive for Language Models
Large language models require iterative updates to address challenges such as knowledge conflicts and outdated information (e. g., incorrect, private, or illegal contents).
DFVO: Learning Darkness-free Visible and Infrared Image Disentanglement and Fusion All at Once
Visible and infrared image fusion is one of the most crucial tasks in the field of image fusion, aiming to generate fused images with clear structural information and high-quality texture features for high-level vision tasks.
RoBridge: A Hierarchical Architecture Bridging Cognition and Execution for General Robotic Manipulation
Operating robots in open-ended scenarios with diverse tasks is a crucial research and application direction in robotics.
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Currently, existing surveys on LLM safety primarily focus on specific stages of the LLM lifecycle, e. g., deployment phase or fine-tuning phase, lacking a comprehensive understanding of the entire "lifechain" of LLMs.
3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians
Building upon this dataset, we introduce AffordSplatNet, a novel model specifically designed for affordance reasoning using 3DGS representations.
DreamFuse: Adaptive Image Fusion with Diffusion Transformer
Image fusion seeks to seamlessly integrate foreground objects with background scenes, producing realistic and harmonious fused images.
Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation
In this work, we propose to learn content and emotion priors as guidance augmented with contrastive learning to learn decoupled content and emotion representation via an innovative Contrastive Decoupled Representation Learning (CDRL) algorithm.
YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multi-Branch Feature Interaction
To address this issue, we propose YOLO-LLTS, an end-to-end real-time traffic sign detection algorithm specifically designed for low-light environments.
VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction
Virtual Try-On (VTON) is a transformative technology in e-commerce and fashion design, enabling realistic digital visualization of clothing on individuals.
Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering
Embodied Question Answering (EQA) is a challenging task in embodied intelligence that requires agents to dynamically explore 3D environments, actively gather visual information, and perform multi-step reasoning to answer questions.
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs
This improvement can even surpass the performance of the best single model in the pool and many existing strong LLMs, confirming it a highly promising paradigm.
DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
In this paper, we propose a Dual-vision Scene Perception Network (DSPNet), to comprehensively integrate multi-view and point cloud features to improve robustness in 3D QA.
Cross-modal Causal Relation Alignment for Video Question Grounding
Video question grounding (VideoQG) requires models to answer the questions and simultaneously infer the relevant video segments to support the answers.
AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay
Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets.
CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond
Unlike existing research, our focus is on the challenges posed by OOD data in real-world applications and on enhancing the robustness and generalization of models.
Randomness of Low-Layer Parameters Determines Confusing Samples in Terms of Interaction Representations of a DNN
In this paper, we find that the complexity of interactions encoded by a deep neural network (DNN) can explain its generalization power.
Pre-Trained Video Generative Models as World Simulators
Video generative models pre-trained on large-scale internet datasets have achieved remarkable success, excelling at producing realistic synthetic videos.
Decoder-Only LLMs are Better Controllers for Diffusion Models
Groundbreaking advancements in text-to-image generation have recently been achieved with the emergence of diffusion models.
A Causality-aware Paradigm for Evaluating Creativity of Multimodal Large Language Models
This game aligns well with the input-output structure of modern multimodal LLMs and benefits from a rich repository of high-quality, human-annotated creative responses, making it an ideal platform for studying LLM creativity.
SR-FoT: A Syllogistic-Reasoning Framework of Thought for Large Language Models Tackling Knowledge-based Reasoning Tasks
Finally, it guides LLMs to use the previously generated major and minor premises to perform syllogistic deductive reasoning to derive the answer to the original question.
Boosting the Dual-Stream Architecture in Ultra-High Resolution Segmentation with Resolution-Biased Uncertainty Estimation
Over the last decade, significant efforts have been dedicated to designing efficient models for the challenge of ultra-high resolution (UHR) semantic segmentation.
PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention
The effect of the former is estimated through intrinsic image decomposition, and the region of the latter is predicted in an additional background effect control branch.
No Pains, More Gains: Recycling Sub-Salient Patches for Efficient High-Resolution Image Recognition
Over the last decade, many notable methods have emerged to tackle the computational resource challenge of the high resolution image recognition (HRIR).
Reproducible Vision-Language Models Meet Concepts Out of Pre-Training
We propose LAION-Beyond benchmark to isolate the evaluation of OOP concepts from pre-training knowledge, with regards to OpenCLIP and its reproducible variants derived from LAION datasets.
Towards Long-Horizon Vision-Language Navigation: Platform, Benchmark and Method
Existing Vision-Language Navigation (VLN) methods primarily focus on single-stage navigation, limiting their effectiveness in multi-stage and long-horizon tasks within complex and dynamic environments.
Category-Adaptive Cross-Modal Semantic Refinement and Transfer for Open-Vocabulary Multi-Label Recognition
The proposed framework consists of two complementary modules, i. e., intra-category semantic refinement (ISR) module and inter-category semantic transfer (IST) module.
DAGSM: Disentangled Avatar Generation with GS-enhanced Mesh
Text-driven avatar generation has gained significant attention owing to its convenience.
Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review
Our findings denote that a majority of recent research works have dealt with the aforementioned challenges by utilizing human-in-the-loop and sim-to-real strategies for the efficient transfer of knowledge from source domains to the target domain under the transfer learning scheme.
Integration of Communication and Computational Imaging
Herein, we propose a novel framework that integrates communication and computational imaging (ICCI) to break through the inherent isolation between communication and computational imaging for remote perception.
High-fidelity and Lip-synced Talking Face Synthesis via Landmark-based Diffusion Model
Some previous methods focus on learning a direct mapping from audio to visual content.
Style-Preserving Lip Sync via Audio-Aware Style Reference
Specifically, we first develop an advanced Transformer-based model adept at predicting lip motion corresponding to the input audio, augmented by the style information aggregated through cross-attention layers from style reference video.
Improving Network Interpretability via Explanation Consistency Evaluation
The pursuit of greater interpretability in neural networks often results in a degradation of their original performance.
VideoQA in the Era of LLMs: An Empirical Study
Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks.
MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection
Learning from pseudo-labels that generated with VLMs~(Vision Language Models) has been shown as a promising solution to assist open vocabulary detection (OVD) in recent studies.
Cool-Fusion: Fuse Large Language Models without Training
We focus on the problem of fusing two or more heterogeneous large language models (LLMs) to facilitate their complementary strengths.
Scaling Up Single Image Dehazing Algorithm by Cross-Data Vision Alignment for Richer Representation Learning and Beyond
Ignoring the domain gap between different data, former de-hazing methods simply adopt multiple datasets for explicit large-scale training, which often makes the methods themselves be violated.
WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models
Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos.
Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram
In modal fusion, we leverage textual clauses to express fine-grained structural and semantic content of geometry diagram, and fuse diagram with textual problem efficiently through structural-semantic pre-training.
Dynamic Correlation Learning and Regularization for Multi-Label Confidence Calibration
To overcome these limitations, we propose the Dynamic Correlation Learning and Regularization (DCLR) algorithm, which leverages multi-grained semantic correlations to better model semantic confusion for adaptive regularization.
Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
In this survey, we give a comprehensive exploration of the latest advancements in Embodied AI.
Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification
(b) A knowledge association module that fuses linguistic and biomedical knowledge into gene priors by transformer-based graph representation learning, capturing the intrinsic relationships between different genes' mutations.
Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior
Large-scale trained diffusion models have a strong generative prior that enables real-world modeling of images to generate diverse and realistic images.
Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection
Specifically, we devise three modules: Background Category-specific Prompt, Background Object Discovery, and Inference Probability Rectification, to empower the detector to discover, represent, and leverage implicit object knowledge explored from background proposals.
Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs
In this study, we propose an axiomatic system to define and quantify the precise memorization and in-context reasoning effects used by the large language model (LLM) for language generation.
Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features
This paper investigates the dynamics of a deep neural network (DNN) learning interactions.
ODMixer: Fine-grained Spatial-temporal MLP for Metro Origin-Destination Prediction
Metro Origin-Destination (OD) prediction is a crucial yet challenging spatial-temporal prediction task in urban computing, which aims to accurately forecast cross-station ridership for optimizing metro scheduling and enhancing overall transport efficiency.
ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning
The rapid development of diffusion models has triggered diverse applications.
Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
To further enhance the robustness of DBP models, we introduce Adversarial Denoising Diffusion Training (ADDT), which incorporates classifier-guided adversarial perturbations into diffusion training, thereby strengthening the DBP models' ability to purify adversarial perturbations.
AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment
In this paper, we present AnimateZoo, a zero-shot diffusion-based video generator to address this challenging cross-species animation issue, aiming to accurately produce animal animations while preserving the background.
IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images
IDF-CR consists of a pixel space cloud removal module (Pixel-CR) and a latent space iterative noise diffusion network (IND).
Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning
For encouraging the agent to well capture the difference brought by perturbation, a perturbation-aware contrastive learning mechanism is further developed by contrasting perturbation-free trajectory encodings and perturbation-based counterparts.
SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection
The quality, quantity, and diversity of the infrared dataset are critical to the detection of small targets.
DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions
Addressing this problem, we modularize a large search space into blocks with small search spaces and develop a family of models with the distilling neural architecture (DNA) techniques.
NiteDR: Nighttime Image De-Raining with Cross-View Sensor Cooperative Learning for Dynamic Driving Scenes
Specifically, we introduce cooperative learning between visible and infrared images captured by different sensors.
AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis
Through extensive experiments across various datasets and scenes, we demonstrate the effectiveness of our approach in facilitating better interaction between LiDAR and camera modalities within a unified neural field.
Mirror Gradient: Towards Robust Multimodal Recommender Systems via Exploring Flat Local Minima
This strategy can implicitly enhance the model's robustness during the optimization process, mitigating instability risks arising from multimodal information inputs.
MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments
To overcome this limitation, we introduce the Multimodal Embodied Interactive Agent (MEIA), capable of translating high-level tasks expressed in natural language into a sequence of executable actions.
TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts
To this end, we propose a 3D scene editing framework, TIPEditor, that accepts both text and image prompts and a 3D bounding box to specify the editing region.
Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition
Specifically, the framework consists of separate global-local adversarial learning modules that learn domain-invariant global and local features independently.
Cross-Domain Facial Expression Recognition
Model Optimization
+2
Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognition
Specifically, an instance-view data hallucination module hallucinates each sample of a novel class to generate new data by employing local semantic correlated attention and global semantic feature fusion derived from base classes.
MirrorDiffusion: Stabilizing Diffusion Process in Zero-shot Image Translation by Prompts Redescription and Beyond
By using a target text prompt for domain adaption, the diffusion model is able to implement zero-shot image-to-image translation advantageously.
Learning Adaptive Spatial Coherent Correlations for Speech-Preserving Facial Expression Manipulation
To capitalize on this insight we propose a novel adaptive spatial coherent correlation learning (ASCCL) algorithm which models the aforementioned correlation as an explicit metric and integrates the metric to supervise manipulating facial expression and meanwhile better preserving the facial animation of spoken contents.
Credible Teacher for Semi-Supervised Object Detection in Open Scene
Credible Teacher adopts an interactive teaching mechanism using flexible labels to prevent uncertain pseudo labels from misleading the model and gradually reduces its uncertainty through the guidance of other credible pseudo labels.
Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach
Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments, advancing the technical roadmap of out-of-distribution (OOD) generalization.
Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation
To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study.
Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering
Attempt to overcome this limitation and inspired by the human top-down reasoning process, i. e., systematically exploring relevant issues to derive a comprehensive answer, this work introduces a novel, explainable multi-agent collaboration framework by leveraging the expansive knowledge of Large Language Models (LLMs) to enhance the capabilities of VLMs themselves.
SQLNet: Scale-Modulated Query and Localization Network for Few-Shot Class-Agnostic Counting
In the localization stage, the Scale-aware Multi-head Localization (SAML) module utilizes the query tensor to predict the confidence, location, and size of each potential object.
Contrastive Transformer Learning with Proximity Data Generation for Text-Based Person Search
Moreover, we propose a proximity data generation (PDG) module to automatically produce more diverse data for cross-modal training.
ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection
Besides, we also observe the theoretical benefits of the LSC coefficient scaling of UNet in the stableness of hidden features and gradient and also robustness.
ADASR: An Adversarial Auto-Augmentation Framework for Hyperspectral and Multispectral Data Fusion
Deep learning-based hyperspectral image (HSI) super-resolution, which aims to generate high spatial resolution HSI (HR-HSI) by fusing hyperspectral image (HSI) and multispectral image (MSI) with deep neural networks (DNNs), has attracted lots of attention.
Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation
In this work, we propose a spatial-temporal knowledge-embedded transformer (STKET) that incorporates the prior spatial-temporal knowledge into the multi-head cross-attention mechanism to learn more representative relationship representations.
A Continual Learning Paradigm for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks
Specifically, our CLVP distills the capabilities of well-trained task-specific models into the visual sub-modules in a stepwise and anti-forgetting manner.
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios.
Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs
Drawing inspiration from the orchestration of diverse specialized agents collaborating to tackle intricate tasks, we propose a framework named Causal-Consistency Chain-of-Thought (CaCo-CoT) that harnesses multi-agent collaboration to bolster the faithfulness and causality of foundation models, involving a set of reasoners and evaluators.
EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
Owing to the combination of the unified architecture and pre-training task, EVE is easy to scale up, enabling better downstream performance with fewer resources and faster training speed.
DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment
Cross-modal garment synthesis and manipulation will significantly benefit the way fashion designers generate garments and modify their designs via flexible linguistic interfaces. Current approaches follow the general text-to-image paradigm and mine cross-modal relations via simple cross-attention modules, neglecting the structural correspondence between visual and textual representations in the fashion design domain.
Coordinate Transformer: Achieving Single-stage Multi-person Mesh Recovery from Videos
Multi-person 3D mesh recovery from videos is a critical first step towards automatic perception of group behavior in virtual reality, physical therapy and beyond.
Understanding Self-attention Mechanism via Dynamical System Perspective
The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models.
LAW-Diffusion: Complex Scene Generation by Diffusion with Layouts
Thanks to the rapid development of diffusion models, unprecedented progress has been witnessed in image synthesis.
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets.
CausalVLR: A Toolbox and Benchmark for Visual-Linguistic Causal Reasoning
We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox containing a rich set of state-of-the-art causal relation discovery and causal inference methods for various visual-linguistic reasoning tasks, such as VQA, image/video captioning, medical report generation, model generalization and robustness, etc.
Exploration and Exploitation of Unlabeled Data for Open-Set Semi-Supervised Learning
In this paper, we address a complex but practical scenario in semi-supervised learning (SSL) named open-set SSL, where unlabeled data contain both in-distribution (ID) and out-of-distribution (OOD) samples.
DreamEditor: Text-Driven 3D Scene Editing with Neural Fields
Neural fields have achieved impressive advancements in view synthesis and scene reconstruction.
DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedback
1) The travel time of a vehicle is delayed feedback on the effectiveness of TSC policy at each traffic intersection since it is obtained after the vehicle has left the road network.
Long-term Wind Power Forecasting with Hierarchical Spatial-Temporal Transformer
In this work, we propose a novel end-to-end wind power forecasting model named Hierarchical Spatial-Temporal Transformer Network (HSTTN) to address the long-term WPF problems.
Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning
Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts.
Identity-Preserving Talking Face Generation with Landmark and Appearance Priors
Prior landmark characteristics of the speaker's face are employed to make the generated landmarks coincide with the facial outline of the speaker.
SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language Models
Our approach can make text-to-image diffusion models easier to use with better user experience, which demonstrates our approach has the potential for further advancing the development of user-friendly text-to-image generation models by bridging the semantic gap between simple narrative prompts and complex keyword-based prompts.
Visual Causal Scene Refinement for Video Question Answering
Our VCSR involves two essential modules: i) the Question-Guided Refiner (QGR) module, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention; ii) the Causal Scene Separator (CSS) module, which discovers a collection of visual causal and non-causal scenes based on the visual-linguistic causal relevance and estimates the causal effect of the scene-separating intervention in a contrastive learning manner.
Multi-object Video Generation from Single Frame Layouts
In this paper, we study video synthesis with emphasis on simplifying the generation conditions.
ASR: Attention-alike Structural Re-parameterization
This technique enables the mitigation of the extra costs for performance improvement during training, such as parameter size and inference time, through these transformations during inference, and therefore SRP has great potential for industrial and practical applications.
Open-World Pose Transfer via Sequential Test-Time Adaption
In open-world conditions, the pose transfer task raises various independent signals: OOD appearance and skeleton, which need to be extracted and distributed in speciality.
Urban Regional Function Guided Traffic Flow Prediction
The prediction of traffic flow is a challenging yet crucial problem in spatial-temporal analysis, which has recently gained increasing interest.
Cross-Modal Causal Intervention for Medical Report Generation
Medical report generation (MRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating the corresponding medical reports according to the given radiology image.
Masked Images Are Counterfactual Samples for Robust Fine-tuning
In this paper, based on causal analysis of the aforementioned problems, we propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation
Vision-Language Navigation (VLN) is a challenging task which requires an agent to align complex visual observations to language instructions to reach the goal position.
AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios
We propose the attention-inspired numerical solver (AttNS), a concise method that helps the generalization and robustness issues faced by the AI-Hybrid numerical solver in solving differential equations due to limited data.
OccluMix: Towards De-Occlusion Virtual Try-on by Semantically-Guided Mixup
Image Virtual try-on aims at replacing the cloth on a personal image with a garment image (in-shop clothes), which has attracted increasing attention from the multimedia and computer vision communities.
Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-identification
We further introduce the Attribute-Aware and Identity-Aware Proxy embedding modules (AAP and IAP) to extract the informative and discriminative feature representations at different stages.
Enhanced Soft Label for Semi-Supervised Semantic Segmentation
As a mainstream framework in the field of semi-supervised learning (SSL), self-training via pseudo labeling and its variants have witnessed impressive progress in semi-supervised semantic segmentation with the recent advance of deep neural networks.
A Retrospect to Multi-prompt Learning across Vision and Language
The vision community is undergoing the unprecedented progress with the emergence of Vision-Language Pretraining Models (VLMs).
RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels
Confidence-wise, we propose a novel sample selection strategy based on confidence representation voting instead of the widely-used small-loss criterion.
UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression
Naturally, we also present a unified multi-task Geometric Transformer framework, Geoformer, to tackle calculation and proving problems simultaneously in the form of sequence generation, which finally shows the reasoning ability can be improved on both two tasks by unifying formulation.
Ranked #5 on
Mathematical Reasoning
on PGPS9K
DreamArtist++: Controllable One-Shot Text-to-Image Generation via Positive-Negative Adapter
To tackle this problem, we propose a simple yet effective framework, namely DreamArtist, which adopts a novel positive-negative prompt-tuning learning strategy on the pre-trained diffusion model, and it has shown to well handle the trade-off between the accurate controllability and fidelity of image generation with only one reference example.
Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels
To reject noisy labels, recent works regard large loss samples as noise but ignore the semantic correlation different multi-label images.
Structure-Preserving 3D Garment Modeling with Neural Sewing Machines
In this paper, we propose a novel Neural Sewing Machine (NSM), a learning-based framework for structure-preserving 3D garment modeling, which is capable of learning representations for garments with diverse shapes and topologies and is successfully applied to 3D garment reconstruction and controllable manipulation.
Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data.
Ranked #6 on
Source-Free Domain Adaptation
on VisDA-2017
Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training
During inference, instead of changing the motion generator, our method reformulates the input text into a masked motion as the prompt for the motion generator to ``reconstruct'' the motion.
A Generic Shared Attention Mechanism for Various Backbone Neural Networks
The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks.
Prompt-Matched Semantic Segmentation
Previous methods usually fine-tuned the entire networks for each specific dataset, which will be burdensome to store massive parameters of these networks.
On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver
The large-scale simulation of dynamical systems is critical in numerous scientific and engineering disciplines.
Robust Real-World Image Super-Resolution against Adversarial Attacks
Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module.
Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering
Existing visual question answering methods often suffer from cross-modal spurious correlations and oversimplified event-level reasoning processes that fail to capture event temporality, causality, and dynamics spanning over the video.
The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network
Recently many plug-and-play self-attention modules (SAMs) are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs).
Adversarially-Aware Robust Object Detector
In this work, we empirically explore the model training for adversarial robustness in object detection, which greatly attributes to the conflict between learning clean images and adversarial images.
Discourse-Aware Graph Networks for Textual Logical Reasoning
In this work, we propose logic structural-constraint modeling to solve the logical reasoning QA and introduce discourse-aware graph networks (DAGNs).
Real-World Image Super-Resolution by Exclusionary Dual-Learning
Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attention with regard to its tremendous application potentials.
Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels
Specifically, an instance-perspective representation blending (IPRB) module is designed to blend the representations of the known labels in an image with the representations of the corresponding unknown labels in another image to complement these unknown labels.
Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels
Multi-label image recognition with partial labels (MLR-PL), in which some labels are known while others are unknown for each image, may greatly reduce the cost of annotation and thus facilitate large-scale MLR.
Multi-Label Image Recognition
Multi-label Image Recognition with Partial Labels
LogicSolver: Towards Interpretable Math Word Problem Solving with Logical Prompt-enhanced Learning
To address this issue and make a step towards interpretable MWP solving, we first construct a high-quality MWP dataset named InterMWP which consists of 11, 495 MWPs and annotates interpretable logical formulas based on algebraic knowledge as the grounded linguistic logic of each solution equation.
Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution
To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera.
Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism
To make ROSETTA automatically determine which experience is available and useful, a prototypical task correlation guided Gating Diversity Controller(GDC) is introduced to adaptively adjust the diversity of gates for the new task based on class-specific prototypes.
Causal Reasoning Meets Visual Representation Learning: A Prospective Study
Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing.
Semantic Representation and Dependency Learning for Multi-Label Image Recognition
We also design an object erasing (OE) module to implicitly learn semantic dependency among categories by erasing semantic-aware regions to regularize the network training.
Open Set Domain Adaptation By Novel Class Discovery
In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain.
Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels
However, these algorithms depend on sufficient multi-label annotations to train the models, leading to poor performance especially with low known label proportion.
Multi-Label Image Recognition
Multi-label Image Recognition with Partial Labels
Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning
To relieve the burden of labor-intensive labeling, deep unsupervised SOD methods have been proposed to exploit noisy labels generated by handcrafted saliency methods.
Semantic-Aware Auto-Encoders for Self-Supervised Representation Learning
Inspired by perceptual learning that could use cross-view learning to perceive concepts and semantics, we propose a novel AE that could learn semantic-aware representation via cross-view image reconstruction.
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels
To reduce the annotation cost, we propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i. e., merely some labels are known while other labels are missing (also called unknown labels) per image.
Multi-Label Image Recognition
Multi-label Image Recognition with Partial Labels
TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning
To overcome these limitations, we take advantage of the multi-scale temporal dependencies within videos and proposes a novel video self-supervised learning framework named Temporal Contrastive Graph Learning (TCGL), which jointly models the inter-snippet and intra-snippet temporal dependencies for temporal representation learning with a hybrid graph contrastive learning strategy.
Aerial Images Meet Crowdsourced Trajectories: A New Approach to Robust Road Extraction
Land remote sensing analysis is a crucial research in earth science.
Ranked #2 on
Semantic Segmentation
on BJRoad
Enhancing Prototypical Few-Shot Learning by Leveraging the Local-Level Strategy
Aiming at recognizing the samples from novel categories with few reference samples, few-shot learning (FSL) is a challenging problem.
Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis
The integration of human parsing and appearance flow effectively guides the generation of video frames with realistic appearance.
Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation
PEMR includes a "looking ahead" process, \textit{i. e.} a visual feature extractor module that estimates feasible paths for gathering 3D navigational information, which is mimicking the human sense of direction.
Road Network Guided Fine-Grained Urban Traffic Flow Inference
Furthermore, we take the road network feature as a query to capture the long-range spatial distribution of traffic flow with a transformer architecture.
Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition
Specifically, we unify a pre-trained acoustic model (wav2vec 2. 0) and a language model (BERT) into an end-to-end trainable framework.
Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
We attribute this ranking correlation problem to the supernet training consistency shift, including feature shift and parameter shift.
Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.
Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.
Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation
Specifically, we propose a Dynamic Reinforced Instruction Attacker (DR-Attacker), which learns to mislead the navigator to move to the wrong target by destroying the most instructive information in instructions at different timesteps.
Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks
Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions.
Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation
In this work, we proposed a novel neural network module termed Heterogeneous Information Aggregation Machine (HIAM), which fully exploits heterogeneous information of historical data (e. g., incomplete OD matrices, unfinished order vectors, and DO matrices) to jointly learn the evolutionary patterns of OD and DO ridership.
Prototypical Graph Contrastive Learning
However, since for a query, its negatives are uniformly sampled from all graphs, existing methods suffer from the critical sampling bias issue, i. e., the negatives likely having the same semantic structure with the query, leading to performance degradation.
Towards Quantifiable Dialogue Coherence Evaluation
To address these limitations, we propose Quantifiable Dialogue Coherence Evaluation (QuantiDCE), a novel framework aiming to train a quantifiable dialogue coherence metric that can reflect the actual human rating standards.
GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoning
Therefore, we propose a Geometric Question Answering dataset GeoQA, containing 4, 998 geometric problems with corresponding annotated programs, which illustrate the solving process of the given problems.
Ranked #6 on
Mathematical Reasoning
on PGPS9K
Solving Inefficiency of Self-supervised Representation Learning
In this paper, we reveal two contradictory phenomena in contrastive learning that we call under-clustering and over-clustering problems, which are major obstacles to learning efficiency.
Ranked #1 on
Self-Supervised Person Re-Identification
on SYSU-30k
Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
In this work, we prove that dynamically adapting network architectures tailored for each domain task along with weight finetuning benefits in both efficiency and effectiveness, compared to the existing image recognition pipeline that only tunes the weights regardless of the architecture.
Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
Prior highly-tuned image parsing models are usually studied in a certain domain with a specific set of semantic labels and can hardly be adapted into other scenarios (e. g., sharing discrepant label granularity) without extensive re-training.
Ranked #1 on
Human Parsing
on 4D-DRESS
(using extra training data)
Unifying Relational Sentence Generation and Retrieval for Medical Image Report Composition
Beyond generating long and topic-coherent paragraphs in traditional captioning tasks, the medical image report composition task poses more task-oriented challenges by requiring both the highly-accurate medical term diagnosis and multiple heterogeneous forms of information including impression and findings.
Temporal Contrastive Graph Learning for Video Action Recognition and Retrieval
To model multi-scale temporal dependencies, our TCGL integrates the prior knowledge about the frame and snippet orders into graph structures, i. e., the intra-/inter- snippet temporal contrastive graphs.
Erasure for Advancing: Dynamic Self-Supervised Learning for Commonsense Reasoning
To solve this issue, we propose a novel DynamIc Self-sUperviSed Erasure (DISUSE) which adaptively erases redundant and artifactual clues in the context and questions to learn and establish the correct corresponding pair relations between the questions and their clues.
Towards a Reliable and Robust Dialogue System for Medical Automatic Diagnosis
To this end, we propose a novel DSMAD agent, INS-DS (Introspective Diagnosis System) comprising of two separate yet cooperative modules, i. e., an inquiry module for proposing symptom-inquiries and an introspective module for deciding when to inform a disease.
Adversarial Training using Contrastive Divergence
To protect the security of machine learning models against adversarial examples, adversarial training becomes the most popular and powerful strategy against various adversarial attacks by injecting adversarial examples into training data.
Linguistically Routing Capsule Network for Out-of-Distribution Visual Question Answering
The experimental results show that our proposed method can improve current VQA models on OOD split without losing performance on the in-domain test data.
CAT-SAC: Soft Actor-Critic with Curiosity-Aware Entropy Temperature
The curiosity is added to the target entropy to increase the entropy temperature for unfamiliar states and decrease the target entropy for familiar states.
AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition
In this work, we explore the correlations among the action units and facial expressions, and devise an AU-Expression Knowledge Constrained Representation Learning (AUE-CRL) framework to learn the AU representations without AU annotations and adaptively use representations to facilitate facial expression recognition.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement
It is crucial since the quality of the evidence is the key to answering commonsense questions, and even determines the upper bound on the QA systems performance.
Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
Besides, we develop a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom correlations in a new disease, which effectively alleviates the needs of a large number of dialogues.
Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition
When sampling tasks in MML-ASR, AMS adaptively determines the task sampling probability for each source language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding
Specifically, we generate the question-answer pair based on both the Visual Genome scene graph and an external knowledge base with controlled programs to disentangle the knowledge from other biases.
Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting
Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting.
Continuous Transition: Improving Sample Efficiency for Continuous Control Problems via MixUp
Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it's still challenging to apply it to real-world tasks, due to the poor sample efficiency.
Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
In this work, we propose an efficient, cooperative and highly automated framework to simultaneously search for all main components including backbone, segmentation branches, and feature fusion module in a unified panoptic segmentation pipeline based on the prevailing one-shot Network Architecture Search (NAS) paradigm.
A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning
Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that deep models are vulnerable to adversarial examples, which are crafted by adding visually imperceptible perturbations to the input images.
Semantically-Aligned Universal Tree-Structured Solver for Math Word Problems
A practical automatic textual math word problems (MWPs) solver should be able to solve various textual MWPs while most existing works only focused on one-unknown linear MWPs.
Ranked #10 on
Math Word Problem Solving
on ALG514
GRADE: Automatic Graph-Enhanced Coherence Metric for Evaluating Open-Domain Dialogue Systems
Capitalized on the topic-level dialogue graph, we propose a new evaluation metric GRADE, which stands for Graph-enhanced Representations for Automatic Dialogue Evaluation.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition
The framework exploits prior knowledge to guide adaptive information propagation among different categories to facilitate multi-label analysis and reduce the dependency of training samples.
Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos
Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval.
Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection
Domain adaptation for object detection tries to adapt the detector from labeled datasets to unlabeled ones for better performance.
Online Alternate Generator against Adversarial Attacks
The field of computer vision has witnessed phenomenal progress in recent years partially due to the development of deep convolutional neural networks.
Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition
In this paper, we propose a novel framework, named Semantics-aware Adaptive Knowledge Distillation Networks (SAKDN), to enhance action recognition in vision-sensor modality (videos) by adaptively transferring and distilling the knowledge from multiple wearable sensors.
Unsupervised Multi-view Clustering by Squeezing Hybrid Knowledge from Cross View and Each View
To ensure that we achieve effective sparse representation and clustering performance on the original data matrix, adaptive graph regularization and unsupervised clustering constraints are also incorporated in the proposed model to preserve the internal structural features of the data.
Component Divide-and-Conquer for Real-World Image Super-Resolution
Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures.
Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning
Although each declares to achieve superior performance, fair comparisons are lacking due to the inconsistent choices of the source/target datasets and feature extractors.
Ranked #1 on
Cross-Domain Facial Expression Recognition
on Source: AFE, Target: CK+, JAFFE, SFEW2.0, FER2013, ExpW
Cross-Domain Facial Expression Recognition
Domain Adaptation
+3
Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition
However, most of these works focus on holistic feature adaptation, and they ignore local features that are more transferable across different datasets.
Cross-Domain Facial Expression Recognition
Facial Expression Recognition (FER)
Fine-Grained Image Captioning with Global-Local Discriminative Objective
This is primarily due to (i) the conservative characteristic of traditional training objectives that drives the model to generate correct but hardly discriminative captions for similar images and (ii) the uneven word distribution of the ground-truth captions, which encourages generating highly frequent words/phrases while suppressing the less frequent but more concrete ones.
EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods.
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning
Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters.
Bidirectional Graph Reasoning Network for Panoptic Segmentation
We introduce a Bidirectional Graph Reasoning Network (BGRNet), which incorporates graph structure into the conventional panoptic segmentation network to mine the intra-modular and intermodular relations within and between foreground things and background stuff classes.
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
To examine the robustness of ReID systems is rather important because the insecurity of ReID systems may cause severe losses, e. g., the criminals may use the adversarial perturbations to cheat the CCTV systems.
Efficient Crowd Counting via Structured Knowledge Transfer
Crowd counting is an application-oriented task and its inference efficiency is crucial for real-world applications.
Linguistically Driven Graph Capsule Network for Visual Question Reasoning
Inspired by the property of a capsule network that can carve a tree structure inside a regular convolutional neural network (CNN), we propose a hierarchical compositional reasoning model called the "Linguistically driven Graph Capsule Network", where the compositional process is guided by the linguistic parse tree.
Towards Causality-Aware Inferring: A Sequential Discriminative Approach for Medical Diagnosis
To eliminate this bias and inspired by the propensity score matching technique with causal diagram, we propose a propensity-based patient simulator to effectively answer unrecorded inquiry by drawing knowledge from the other records; Bias (ii) inherently comes along with the passively collected data, and is one of the key obstacles for training the agent towards "learning how" rather than "remembering what".
DDet: Dual-path Dynamic Enhancement Network for Real-World Image Super-Resolution
Previous image SR methods fail to exhibit similar performance on Real-SR as the image data is not aligned inherently.
Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread
The proposed algorithm for the first time achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video
Temporally language grounding in untrimmed videos is a newly-raised task in video understanding.
Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
To address this problem, we model a metro system as graphs with various topologies and propose a unified Physical-Virtual Collaboration Graph Network (PVCGN), which can effectively learn the complex ridership patterns from the tailor-designed graphs.
An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation
In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations.
Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
Moreover, we find that the knowledge of a network model lies not only in the network parameters but also in the network architecture.
Knowledge Graph Transfer Network for Few-Shot Recognition
In this work, we represent the semantic correlations in the form of structured knowledge graph and integrate this graph into deep neural networks to promote few-shot learning by a novel Knowledge Graph Transfer Network (KGTN).
A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models
To solve this problem, we derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation.
Layout-Graph Reasoning for Fashion Landmark Detection
Each Layout-Graph Reasoning(LGR) layer aims to map feature representations into structural graph nodes via a Map-to-Node module, performs reasoning over structural graph nodes to achieve global layout coherency via a layout-graph reasoning module, and then maps graph nodes back to enhance feature representations via a Node-to-Map module.
Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning
Resembling the rapid learning capability of human, few-shot learning empowers vision systems to understand new concepts by training with few samples.
Ranked #21 on
Few-Shot Object Detection
on MS-COCO (30-shot)
