Search Results for author:
Found 341 papers, 192 papers with code
LLMTune: Accelerate Database Knob Tuning with Large Language Models
Database knob tuning is a critical challenge in the database community, aiming to optimize knob values to enhance database performance for specific workloads.
Importance Weighted Adversarial Nets for Partial Domain Adaptation
This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less number of classes compared to the source domain.
AlignBench: Benchmarking Chinese Alignment of Large Language Models
We will provide public APIs for evaluating AlignBench with CritiqueLLM to facilitate the evaluation of LLMs' Chinese alignment.
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
In this paper, we show the surprisingly good capabilities of plain vision transformers for pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model called ViTPose.
Ranked #1 on
Pose Estimation
on COCO test-dev
ViTPose++: Vision Transformer for Generic Body Pose Estimation
In this paper, we show the surprisingly good properties of plain vision transformers for body pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model dubbed ViTPose.
Ranked #1 on
Animal Pose Estimation
on AP-10K
(using extra training data)
Bridging Composite and Real: Towards End-to-end Deep Image Matting
Furthermore, we provide a benchmark containing 2, 000 high-resolution real-world animal images and 10, 000 portrait images along with their manually labeled alpha mattes to serve as a test bed for evaluating matting model's generalization ability on real-world images.
Ranked #2 on
Image Matting
on AM-2K
GMFlow: Learning Optical Flow via Global Matching
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements.
Ranked #8 on
Optical Flow Estimation
on Spring
Unifying Flow, Stereo and Depth Estimation
We present a unified formulation and model for three motion and 3D perception tasks: optical flow, rectified stereo matching and unrectified stereo depth estimation from posed images.
Ranked #1 on
Optical Flow Estimation
on Sintel-clean
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model
In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS.
HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpainting
Given a generated failed image due to malformed hands, we utilize ControlNet modules to re-inject such correct hand information.
ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond
Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism.
Ranked #2 on
Image Classification
on ImageNet ReaL
Audio-Visual Segmentation
To deal with the AVS problem, we propose a novel method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process.
Audio-Visual Segmentation with Semantics
To deal with these problems, we propose a new baseline method that uses a temporal pixel-wise audio-visual interaction module to inject audio semantics as guidance for the visual segmentation process.
An Empirical Study of Remote Sensing Pretraining
To this end, we train different networks from scratch with the help of the largest RS scene recognition dataset up to now -- MillionAID, to obtain a series of RS pretrained backbones, including both convolutional neural networks (CNN) and vision transformers such as Swin and ViTAE, which have shown promising performance on computer vision tasks.
Ranked #1 on
Aerial Scene Classification
on UCM (80% as trainset)
Aerial Scene Classification
Building change detection for remote sensing images
+5
Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model
Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability.
Ranked #1 on
Aerial Scene Classification
on AID (50% as trainset)
Deep Learning for Camera Calibration and Beyond: A Survey
In this paper, we provide a comprehensive survey of learning-based camera calibration techniques, by analyzing their strengths and limitations.
Deep Automatic Natural Image Matting
To address the problem, a novel end-to-end matting network is proposed, which can predict a generalized trimap for any image of the above types as a unified semantic representation.
Ranked #2 on
Image Matting
on AIM-500
Uncertainty Inspired RGB-D Saliency Detection
Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution.
Ranked #1 on
RGB-D Salient Object Detection
on LFSD
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
Graph representation learning has emerged as a powerful technique for addressing real-world problems.
Privacy-Preserving Portrait Matting
We systematically evaluate both trimap-free and trimap-based matting methods on P3M-10k and find that existing matting methods show different generalization capabilities when following the Privacy-Preserving Training (PPT) setting, i. e., training on face-blurred images and testing on arbitrary images.
Ranked #3 on
Image Matting
on P3M-10k
ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
Nevertheless, vision transformers treat an image as 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance.
Ranked #2 on
Video Object Segmentation
on DAVIS 2017
DUT: Learning Video Stabilization by Simply Watching Unstable Videos
In this paper, we attempt to tackle the video stabilization problem in a deep unsupervised learning manner, which borrows the divide-and-conquer idea from traditional stabilizers while leveraging the representation power of DNNs to handle the challenges in real-world scenarios.
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously.
Ranked #1 on
Text Spotting
on Total-Text
(using extra training data)
DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting
In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with explicit points solo for text detection, recognition, and script identification simultaneously.
Ranked #1 on
Text Spotting
on Inverse-Text
RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL
Due to the structural property of the SQL queries, the seq2seq model takes the responsibility of parsing both the schema items (i. e., tables and columns) and the skeleton (i. e., SQL keywords).
Ranked #1 on
Semantic Parsing
on spider
Transferable and Efficient Non-Factual Content Detection via Probe Training with Offline Consistency Checking
Detecting non-factual content is a longstanding goal to increase the trustworthiness of large language models (LLMs) generations.
DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
Even though trained mainly on images, we discover that pretrained diffusion models show impressive power in guiding sketch synthesis.
Referring Image Matting
Different from conventional image matting, which either requires user-defined scribbles/trimap to extract a specific foreground object or directly extracts all the foreground objects in the image indiscriminately, we introduce a new task named Referring Image Matting (RIM) in this paper, which aims to extract the meticulous alpha matte of the specific object that best matches the given natural language description, thus enabling a more natural and simpler instruction for image matting.
Ranked #1 on
Referring Image Matting (RefMatte-RW100)
on RefMatte
Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics
Unsupervised monocular depth and ego-motion estimation has drawn extensive research attention in recent years.
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process.
Ranked #4 on
RGB-D Salient Object Detection
on LFSD
The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT
Overall KiTS21 facilitated a significant advancement in the state of the art in kidney tumor segmentation, and provides useful insights that are applicable to the field of semantic segmentation as a whole.
DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
However, these methods built upon detection transformer framework might achieve sub-optimal training efficiency and performance due to coarse positional query modeling. In addition, the point label form exploited in previous works implies the reading order of humans, which impedes the detection robustness from our observation.
Ranked #3 on
Scene Text Detection
on SCUT-CTW1500
Deep Image Matting: A Comprehensive Survey
Image matting refers to extracting precise alpha matte from natural images, and it plays a critical role in various downstream applications, such as image editing.
Progressive LiDAR Adaptation for Road Detection
To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection, because LiDAR data is less susceptible to visual noises.
VSA: Learning Varied-Size Window Attention in Vision Transformers
Attention within windows has been widely explored in vision transformers to balance the performance, computation complexity, and memory footprint.
Weakly-Supervised Salient Object Detection via Scribble Annotations
In this paper, we propose a weakly-supervised salient object detection model to learn saliency from such annotations.
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment.
Ranked #24 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
In terms of the AMG mode, Hi-SAM segments text stroke foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing.
Ranked #1 on
Hierarchical Text Segmentation
on HierText
AP-10K: A Benchmark for Animal Pose Estimation in the Wild
The experimental results provide sound empirical evidence on the superiority of learning from diverse animals species in terms of both accuracy and generalization ability.
APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking
Based on APT-36K, we benchmark several representative models on the following three tracks: (1) supervised animal pose estimation on a single frame under intra- and inter-domain transfer learning settings, (2) inter-species domain generalization test for unseen animals, and (3) animal pose estimation with animal tracking.
Vision Transformer with Quadrangle Attention
Window-based attention has become a popular choice in vision transformers due to its superior performance, lower computational complexity, and less memory footprint.
P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds
Point cloud completion aims to recover the complete shape based on a partial observation.
ISNet: Shape Matters for Infrared Small Target Detection
TOAA block calculates the low-level information with attention mechanism in both row and column directions and fuses it with the high-level information to capture the shape characteristic of targets and suppress noises.
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity.
Ranked #10 on
Scene Text Recognition
on ICDAR2015
(using extra training data)
SVGDreamer: Text Guided SVG Generation with Diffusion Model
However, existing text-to-SVG generation methods lack editability and struggle with visual quality and result diversity.
Pruning Self-attentions into Convolutional Layers in Single Path
Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers.
Ranked #18 on
Efficient ViTs
on ImageNet-1K (with DeiT-T)
MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining
However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks.
Ranked #1 on
Semantic Segmentation
on SpaceNet 1
(using extra training data)
Aerial Scene Classification
Building change detection for remote sensing images
+13
Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers
In DQFA, a novel domain query is used to aggregate and align global context from the token sequence of both domains.
A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning
With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed.
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering
Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning.
SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection
We observe that the prevailing set abstraction design for down-sampling points may maintain too much unimportant background information that can affect feature learning for detecting objects.
Event-based Simultaneous Localization and Mapping: A Comprehensive Survey
This paper presents a timely and comprehensive review of event-based vSLAM algorithms that exploit the benefits of asynchronous and irregular event streams for localization and mapping tasks.
Towards Data-Efficient Detection Transformers
Besides, we introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency.
Rethinking Portrait Matting with Privacy Preserving
P3M-10k consists of 10, 421 high resolution face-blurred portrait images along with high-quality alpha mattes, which enables us to systematically evaluate both trimap-free and trimap-based matting methods and obtain some useful findings about model generalization ability under the privacy preserving training (PPT) setting.
Ranked #1 on
Image Matting
on P3M-10k
JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes
A naive way is to accomplish them independently in a sequential or parallel manner, but there are many drawbacks, i. e., 1) the depth and VO results suffer from the inherent scale ambiguity issue; 2) the BEV layout is directly predicted from the front-view image without using any depth-related information, although the depth map contains useful geometry clues for inferring scene layouts.
CodeS: Towards Building Open-source Language Models for Text-to-SQL
To address the limitations, we introduce CodeS, a series of pre-trained language models with parameters ranging from 1B to 15B, specifically designed for the text-to-SQL task.
Simultaneously Localize, Segment and Rank the Camouflaged Objects
With the above understanding about camouflaged objects, we present the first ranking based COD network (Rank-Net) to simultaneously localize, segment and rank camouflaged objects.
Towards Deeper Understanding of Camouflaged Object Detection
With the above understanding about camouflaged objects, we present the first triple-task learning framework to simultaneously localize, segment, and rank camouflaged objects, indicating the conspicuousness level of camouflage.
Progressive One-shot Human Parsing
In this paper, we devise a novel Progressive One-shot Parsing network (POPNet) to address two critical challenges , i. e., testing bias and small sizes.
End-to-end One-shot Human Parsing
To address three main challenges in OSHP, i. e., small sizes, testing bias, and similar parts, we devise an End-to-end One-shot human Parsing Network (EOP-Net).
I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection
Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i. e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate detections of arbitrary-shaped text instances with diverse background context.
Ranked #5 on
Scene Text Detection
on SCUT-CTW1500
Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection
In this way, our model can form a more explicit and discriminative decision boundary to distinguish known and also unseen anomalies from normal samples more effectively.
Ranked #3 on
Supervised Anomaly Detection
on MVTec AD
(using extra training data)
Bi-Temporal Semantic Reasoning for the Semantic Change Detection in HR Remote Sensing Images
Recent studies indicate that the SCD can be modeled through a triple-branch Convolutional Neural Network (CNN), which contains two temporal branches and a change branch.
GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds
Technically, a global-local transformer (GLT) module is employed to integrate object- and patch-aware prior into seed point features to effectively form strong feature representation for geometric positions of the seed points, thus providing more robust and accurate cues for offset learning.
OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking
By integrating the derived classification scores with the center-ness scores, the resulting network can effectively suppress interference proposals and further mitigate task misalignment.
BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye View
The spatial information indicating objects' spatial adjacency across consecutive frames is crucial for effective object tracking.
Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing
In this paper, we propose a novel GRAph PYramid Mutual Learning (Grapy-ML) method to address the cross-dataset human parsing problem, where the annotations are at different granularities.
GLM-Dialog: Noise-tolerant Pre-training for Knowledge-grounded Dialogue Generation
We present GLM-Dialog, a large-scale language model (LLM) with 10B parameters capable of knowledge-grounded conversation in Chinese using a search engine to access the Internet knowledge.
One-Shot Affordance Detection
To empower robots with this ability in unseen scenarios, we consider the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.
One-Shot Object Affordance Detection in the Wild
To empower robots with this ability in unseen scenarios, we first study the challenging one-shot affordance detection problem in this paper, i. e., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.
RGB-D Saliency Detection via Cascaded Mutual Information Minimization
In this paper, we introduce a novel multi-stage cascaded learning framework via mutual information minimization to "explicitly" model the multi-modal information between RGB image and depth data.
AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
Despite making significant progress in multi-modal tasks, current Multi-modal Large Language Models (MLLMs) encounter the significant challenge of hallucinations, which may lead to harmful consequences.
Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images
To overcome this limitation, we propose a Wide-Context Network (WiCoNet) for the semantic segmentation of HR RSIs.
PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation
The Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously.
Salient Objects in Clutter
This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
Dynamic Focus-aware Positional Queries for Semantic Segmentation
In this paper, we propose a simple yet effective query design for semantic segmentation termed Dynamic Focus-aware Positional Queries (DFPQ), which dynamically generates positional queries conditioned on the cross-attention scores from the preceding decoder block and the positional encodings for the corresponding image features, simultaneously.
Ranked #21 on
Semantic Segmentation
on ADE20K
Nighttime Dehazing with a Synthetic Benchmark
To address this issue, we propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images, which first reconstructs the scene geometry, then simulates the light rays and object reflectance, and finally renders the haze effects.
Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning
Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast majority ones to ease storage burden and optimization difficulty.
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios
We introduce TableLLM, a robust large language model (LLM) with 13 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to real-world office scenarios.
Dense Uncertainty Estimation
Deep neural networks can be roughly divided into deterministic neural networks and stochastic neural networks. The former is usually trained to achieve a mapping from input space to output space via maximum likelihood estimation for the weights, which leads to deterministic predictions during testing.
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection
Visual salient object detection (SOD) aims at finding the salient object(s) that attract human attention, while camouflaged object detection (COD) on the contrary intends to discover the camouflaged object(s) that hidden in the surrounding.
Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline
We also propose a new 3D VQA framework to effectively predict the completely visually grounded and explainable answer.
A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance.
SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation
However, we observe two problems with this naive pipeline: (1) the domain gap between natural objects and surgical instruments leads to inferior generalisation of SAM; and (2) SAM relies on precise point or box locations for accurate segmentation, requiring either extensive manual guidance or a well-performing specialist detector for prompt preparation, which leads to a complex multi-stage pipeline.
SurgicalPart-SAM: Part-to-Whole Collaborative Prompting for Surgical Instrument Segmentation
Specifically, we achieve this by proposing (1) Collaborative Prompts that describe instrument structures via collaborating category-level and part-level texts; (2) Cross-Modal Prompt Encoder that encodes text prompts jointly with visual embeddings into discriminative part-level representations; and (3) Part-to-Whole Adaptive Fusion and Hierarchical Decoding that adaptively fuse the part-level representations into a whole for accurate instrument segmentation in surgical scenarios.
Weakly Supervised Video Salient Object Detection
Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain.
DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification
Hyperspectral image (HSI) classification is challenging due to spatial variability caused by complex imaging conditions.
Recurrent Glimpse-based Decoder for Detection with Transformer
Then, a glimpse-based decoder is introduced to provide refined detection results based on both the glimpse features and the attention modeling outputs of the previous stage.
Ranked #1 on
Object Detection
on MS COCO
(GFlops metric)
Generative Transformer for Accurate and Reliable Salient Object Detection
For the former, we apply transformer to a deterministic model, and explain that the effective structure modeling and global context modeling abilities lead to its superior performance compared with the CNN based frameworks.
Learning Affordance Grounding from Exocentric Images
To empower an agent with such ability, this paper proposes a task of affordance grounding from exocentric view, i. e., given exocentric human-object interaction and egocentric object images, learning the affordance knowledge of the object and transferring it to the egocentric image using only the affordance label as supervision.
Grounded Affordance from Exocentric View
Due to the diversity of interactive affordance, the uniqueness of different individuals leads to diverse interactions, which makes it difficult to establish an explicit link between object parts and affordance labels.
ReAct: Temporal Action Detection with Relational Queries
Moreover, we propose two losses to facilitate and stabilize the training of action classification.
Ranked #15 on
Temporal Action Localization
on THUMOS’14
FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing Network
Single image dehazing is a critical image pre-processing step for subsequent high-level computer vision tasks.
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge
Given a text description, we immediately imagine an overall visual impression using this prior and, based on this, we draw a picture by progressively adding more and more details.
Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
Cold-start problem is a fundamental challenge for recommendation tasks.
RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?
In this paper, we make the first attempt to demonstrate the importance of both regions in cropping from a complete perspective and propose a simple yet effective pretext task called Region Contrastive Learning (RegionCL).
GLT-T++: Global-Local Transformer for 3D Siamese Tracking with Ranking Loss
Incorporating this transformer-based voting scheme into 3D RPN, a novel Siamese method dubbed GLT-T is developed for 3D single object tracking on point clouds.
Web-Scale Academic Name Disambiguation: the WhoIsWho Benchmark, Leaderboard, and Toolkit
The toolkit is at https://github. com/THUDM/WhoIsWho.
Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images
Semantic Change Detection (SCD) refers to the task of simultaneously extracting the changed areas and the semantic categories (before and after the changes) in Remote Sensing Images (RSIs).
Ranked #1 on
Change Detection
on SECOND
GraMMaR: Ground-aware Motion Model for 3D Human Motion Reconstruction
Demystifying complex human-ground interactions is essential for accurate and realistic 3D human motion reconstruction from RGB videos, as it ensures consistency between the humans and the ground plane.
Graph Contrastive Learning for Anomaly Detection
To achieve the contrastive objective, we design a graph neural network encoder that can infer and further remove suspicious links during message passing, as well as learn the global context of the input graph.
Panther: Fast Top-k Similarity Search in Large Networks
The algorithm is based on a novel idea of random path, and an extended method is also presented, to enhance the structural similarity when two vertices are completely disconnected.
Social and Information Networks
CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose
Motivated by the progress of visual-language research, we propose that pre-trained language models (e. g., CLIP) can facilitate animal pose estimation by providing rich prior knowledge for describing animal keypoints in text.
MirrorGAN: Learning Text-to-image Generation by Redescription
Generating an image from a given text description has two goals: visual realism and semantic consistency.
Ranked #8 on
Text-to-Image Generation
on CUB
(Inception score metric)
Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization
However, since the view outside the boundary is not available during warping, the resulting holes around the boundary of the stabilized frame must be discarded (i. e., cropping) to maintain visual consistency, and thus does leads to a tradeoff between stability and cropping ratio.
BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation
Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more practical setting due to the data privacy, security, and transmission issues.
Towards High Performance Human Keypoint Detection
Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance.
Ranked #5 on
Pose Estimation
on COCO test-dev
Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender System
In recent years, thanks to the rapid development of deep learning (DL), DL-based multi-task learning (MTL) has made significant progress, and it has been successfully applied to recommendation systems (RS).
FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e. g., X-Ray, CT, and MRI) and analysis tasks (e. g., classification, detection, and segmentation).
ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution
Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation.
Data-driven Estimation of Origin-Destination Demand and User Cost Functions for the Optimization of Transportation Networks
In earlier work (Zhang et al., 2016) we used actual traffic data from the Eastern Massachusetts transportation network in the form of spatial average speeds and road segment flow capacities in order to estimate Origin-Destination (OD) flow demand matrices for the network.
Systems and Control 90B06
Data-Driven Estimation of Travel Latency Cost Functions via Inverse Optimization in Multi-Class Transportation Networks
We develop a method to estimate from data travel latency cost functions in multi-class transportation networks, which accommodate different types of vehicles with very different characteristics (e. g., cars and trucks).
Systems and Control Optimization and Control 90C33, 90C90, 90C30
LineaRE: Simple but Powerful Knowledge Graph Embedding for Link Prediction
Specifically, we regard knowledge graph embedding as a simple linear regression task, where a relation is modeled as a linear function of two low-dimensional vector-presented entities with two weight vectors and a bias vector.
Ranked #1 on
Link Prediction
on FB15k
Confidence-Aware Learning for Camouflaged Object Detection
Then, we concatenate it with the input image and feed it to the confidence estimation network to produce an one channel confidence map. We generate dynamic supervision for the confidence estimation network, representing the agreement of camouflage prediction with the ground truth camouflage map.
RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation
However, it lacks proficiency in referring video object segmentation (RVOS) due to the need for precise user-interactive prompts and a limited understanding of different modalities, such as language and vision.
Statistical Anomaly Detection via Composite Hypothesis Testing for Markov Models
Under Markovian assumptions, we leverage a Central Limit Theorem (CLT) for the empirical measure in the test statistic of the composite hypothesis Hoeffding test so as to establish weak convergence results for the test statistic, and, thereby, derive a new estimator for the threshold needed by the test.
DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
In addition, feature-level alignment is carried out by aligning the feature maps of the source and target images from student network using a weighted maximum mean discrepancy loss.
Ranked #18 on
Synthetic-to-Real Translation
on SYNTHIA-to-Cityscapes
Auto Learning Attention
Attention modules have been demonstrated effective in strengthening the representation ability of a neural network via reweighting spatial or channel features or stacking both operations sequentially.
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
Since data augmentation strategies have largely alleviated the training instability, how to further improve the generative performance of DE-GANs becomes a hotspot.
Deep Interest Highlight Network for Click-Through Rate Prediction in Trigger-Induced Recommendation
In many classical e-commerce platforms, personalized recommendation has been proven to be of great business value, which can improve user satisfaction and increase the revenue of platforms.
Toward Real-world Single Image Deraining: A New Benchmark and Beyond
To address these issues, we establish a new high-quality dataset named RealRain-1k, consisting of $1, 120$ high-resolution paired clean and rainy images with low- and high-density rain streaks, respectively.
SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection
Multi-view camera-based 3D object detection has become popular due to its low cost, but accurately inferring 3D geometry solely from camera data remains challenging and may lead to inferior performance.
A Semi-supervised Nighttime Dehazing Baseline with Spatial-Frequency Aware and Realistic Brightness Constraint
There are two distinctions between nighttime and daytime haze.
Understanding WeChat User Preferences and "Wow" Diffusion
"Top Stories" is a novel friend-enhanced recommendation engine in WeChat, in which users can read articles based on preferences of both their own and their friends.
Graph Representation Learning
Social and Information Networks
An Energy-Based Prior for Generative Saliency
We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution.
HOSMEL: A Hot-Swappable Modularized Entity Linking Toolkit for Chinese
We investigate the usage of entity linking (EL)in downstream tasks and present the first modularized EL toolkit for easy task adaptation.
RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimation
Recently, the RGB images and point clouds fusion methods have been proposed to jointly estimate 2D optical flow and 3D scene flow.
Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach
On the one hand, the framework enables training multiple supervised ranking models upon the pseudo labels produced by multiple unsupervised ranking models.
Invertible Attention
Attention has been proved to be an efficient mechanism to capture long-range dependencies.
Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter
The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes.
Transmission-Guided Bayesian Generative Model for Smoke Segmentation
To effectively model the two types of uncertainty, we introduce a Bayesian generative model to simultaneously estimate the posterior distribution of model parameters and its predictions.
Scalable Mask Annotation for Video Text Spotting
Video text spotting refers to localizing, recognizing, and tracking textual elements such as captions, logos, license plates, signs, and other forms of text within consecutive video frames.
Watermarking for Out-of-distribution Detection
Out-of-distribution (OOD) detection aims to identify OOD data based on representations extracted from well-trained deep models.
Ranked #20 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
Forest Fire Clustering for Single-cell Sequencing with Iterative Label Propagation and Parallelized Monte Carlo Simulation
Here, we introduce Forest Fire Clustering, an efficient and interpretable method for cell-type discovery from single-cell data.
GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
In response to this issue, we propose to efficiently turn an off-the-shelf query-based image text spotter into a specialist on video and present a simple baseline termed GoMatching, which focuses the training efforts on tracking while maintaining strong recognition performance.
Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images
In this paper, we propose a novel stagewise domain adaptation model called RoadDA to address the DS issue in this field.
Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation
In addition to previous methods that seek correspondences by hand-crafted or learnt geometric features, recent point cloud registration methods have tried to apply RGB-D data to achieve more accurate correspondence.
Multimodal Variational Auto-encoder based Audio-Visual Segmentation
To achieve this, our ECMVAE factorizes the representations of each modality with a modality-shared representation and a modality-specific representation.
Improving Weak-to-Strong Generalization with Scalable Oversight and Ensemble Learning
In the first phase, based on human supervision, the quality of weak supervision is enhanced through a combination of scalable oversight and ensemble learning, reducing the capability gap between weak teachers and strong students.
On Robust Cross-View Consistency in Self-Supervised Monocular Depth Estimation
Compared with the photometric consistency loss as well as the rigid point cloud alignment loss, the proposed DFA and VDA losses are more robust owing to the strong representation power of deep features as well as the high tolerance of voxel density to the aforementioned challenges.
Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection
In particular, following the principle of disentangled representation learning, we introduce a mutual information upper bound with a mutual information minimization regularizer to encourage the disentangled representation of each modality for salient object detection.
CODE: Contrastive Pre-training with Adversarial Fine-tuning for Zero-shot Expert Linking
In this paper, we propose CODE, which first pre-trains an expert linking model by contrastive learning on AMiner such that it can capture the representation and matching patterns of experts without supervised signals, then it is fine-tuned between AMiner and external sources to enhance the models transferability in an adversarial manner.
ESceme: Vision-and-Language Navigation with Episodic Scene Memory
Vision-and-language navigation (VLN) simulates a visual agent that follows natural-language navigation instructions in real-world scenes.
MPMQA: Multimodal Question Answering on Product Manuals
Taking into account the length of product manuals and the fact that a question is always related to a small number of pages, MPMQA can be naturally split into two subtasks: retrieving most related pages and then generating multimodal answers.
GETAM: Gradient-weighted Element-wise Transformer Attention Map for Weakly-supervised Semantic segmentation
To bridge their gap, a Class Activation Map (CAM) is usually generated to provide pixel level pseudo labels.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Learning to Learn Better for Video Object Segmentation
Recently, the joint learning framework (JOINT) integrates matching based transductive reasoning and online inductive learning to achieve accurate and robust semi-supervised video object segmentation (SVOS).
Latent-based Diffusion Model for Long-tailed Recognition
We propose a new approach, the Latent-based Diffusion Model for Long-tailed Recognition (LDMLR), as a feature augmentation method to tackle the issue.
Wide-angle Image Rectification: A Survey
In this paper, we comprehensively survey progress in wide-angle image rectification from transformation models to rectification methods.
RU-Net: Regularized Unrolling Network for Scene Graph Generation
Scene graph generation (SGG) aims to detect objects and predict the relationships between each pair of objects.
Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation
To solve this, most existing approaches follow a multi-training pipeline to refine CAMs for better pseudo-labels, which includes: 1) re-training the classification model to generate CAMs; 2) post-processing CAMs to obtain pseudo labels; and 3) training a semantic segmentation model with the obtained pseudo labels.
Ranked #22 on
Weakly-Supervised Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
Memory-Gated Recurrent Networks
The essence of multivariate sequential learning is all about how to extract dependencies in data.
Chain of Thought Prompting Elicits Knowledge Augmentation
The knowledge-augmented deep learning paradigm refers to a paradigm in which domain knowledge is identified and integrated into deep models.
Siamese Network with Interactive Transformer for Video Object Segmentation
Semi-supervised video object segmentation (VOS) refers to segmenting the target object in remaining frames given its annotation in the first frame, which has been actively studied in recent years.
From heavy rain removal to detail restoration: A faster and better network
This approach comprises two key modules, a rain streaks removal network (R$^2$Net) focusing on accurate rain removal, and a details reconstruction network (DRNet) designed to recover the textural details of rain-free images.
Energy-Based Residual Latent Transport for Unsupervised Point Cloud Completion
Unsupervised point cloud completion aims to infer the whole geometry of a partial object observation without requiring partial-complete correspondence.
DA-STC: Domain Adaptive Video Semantic Segmentation via Spatio-Temporal Consistency
To solve the challenge, we propose a novel DA-STC method for domain adaptive video semantic segmentation, which incorporates a bidirectional multi-level spatio-temporal fusion module and a category-aware spatio-temporal feature alignment module to facilitate consistent learning for domain-invariant features.
Training A Small Emotional Vision Language Model for Visual Art Comprehension
This paper develops small vision language models to understand visual art, which, given an art work, aims to identify its emotion category and explain this prediction with natural language.
Energy-Based Generative Cooperative Saliency Prediction
In this paper, to model the uncertainty of visual saliency, we study the saliency prediction problem from the perspective of generative models by learning a conditional probability distribution over the saliency map given an input image, and treating the saliency prediction as a sampling process from the learned distribution.
Exemplar-free Class Incremental Learning via Discriminative and Comparable One-class Classifiers
DisCOIL follows the basic principle of POC, but it adopts variational auto-encoders (VAE) instead of other well-established one-class classifiers (e. g. deep SVDD), because a trained VAE can not only identify the probability of an input sample belonging to a class but also generate pseudo samples of the class to assist in learning new tasks.
Human-imperceptible, Machine-recognizable Images
Massive human-related data is collected to train neural networks for computer vision tasks.
FHA-Kitchens: A Novel Dataset for Fine-Grained Hand Action Recognition in Kitchen Scenes
We represent the action information in each hand interaction region as a triplet, resulting in a total of 878 action triplets.
APTv2: Benchmarking Animal Pose Estimation and Tracking with a Large-scale Dataset and Beyond
Animal Pose Estimation and Tracking (APT) is a critical task in detecting and monitoring the keypoints of animals across a series of video frames, which is essential for understanding animal behavior.
Open-World Semi-Supervised Learning for Node Classification
Open-world semi-supervised learning (Open-world SSL) for node classification, that classifies unlabeled nodes into seen classes or multiple novel classes, is a practical but under-explored problem in the graph community.
TAVGBench: Benchmarking Text to Audible-Video Generation
To support research in this field, we have developed a comprehensive Text to Audible-Video Generation Benchmark (TAVGBench), which contains over 1. 7 million clips with a total duration of 11. 8 thousand hours.
Learning structure-aware semantic segmentation with image-level supervision
Within this pipeline, the class activation map (CAM) is obtained and further processed to serve as a pseudo label to train the semantic segmentation model in a fully-supervised manner.
Multi-grained Hypergraph Interest Modeling for Conversational Recommendation
In our approach, we first employ the hypergraph structure to model users' historical dialogue sessions and form a session-based hypergraph, which captures coarse-grained, session-level relations.
Decoupling Learning and Remembering: A Bilevel Memory Framework With Knowledge Projection for Task-Incremental Learning
BMKP decouples the functions of learning and knowledge remembering via a bilevel-memory design: a working memory responsible for adaptively model learning, to ensure plasticity; a long-term memory in charge of enduringly storing the knowledge incorporated within the learned model, to guarantee stability.
Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming
We show the equivalence of the Gibbs distribution to a message-passing algorithm by the properties of the Gumbel distribution and give all the ingredients required for variational Bayesian inference of a latent path, namely Bayesian dynamic programming (BDP).
Localizing Scan Targets from Human Pose for Autonomous Lung Ultrasound Imaging
Ultrasound is progressing toward becoming an affordable and versatile solution to medical imaging.
Leverage Interactive Affinity for Affordance Learning
Perceiving potential "action possibilities" (i. e., affordance) regions of images and learning interactive functionalities of objects from human demonstration is a challenging task due to the diversity of human-object interactions.
Weakly-supervised Contrastive Learning for Unsupervised Object Discovery
Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of objects from the background within a scene without relying on labeled datasets, which benefits the task of bounding-box-level localization and pixel-level segmentation.
Transferable Attack for Semantic Segmentation
We analysis performance of semantic segmentation models wrt.
IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models
We present a diffusion-based image morphing approach with perceptually-uniform sampling (IMPUS) that produces smooth, direct and realistic interpolations given an image pair.
SGSH: Stimulate Large Language Models with Skeleton Heuristics for Knowledge Base Question Generation
Knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB.
Registration of multi-view point sets under the perspective of expectation-maximization
Registration of multi-view point sets is a prerequisite for 3D model reconstruction.
Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning
Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points.
Rethinking Polyp Segmentation from an Out-of-Distribution Perspective
Unlike existing fully-supervised approaches, we rethink colorectal polyp segmentation from an out-of-distribution perspective with a simple but effective self-supervised learning approach.
Neural Operators for Delay-Compensating Control of Hyperbolic PIDEs
The recently introduced DeepONet operator-learning framework for PDE control is extended from the results for basic hyperbolic and parabolic PDEs to an advanced hyperbolic class that involves delays on both the state and the system output or input.
Object-aware Adaptive-Positivity Learning for Audio-Visual Question Answering
These selected pairs are constrained to have larger similarity values than the mismatched pairs.
Audio-visual Question Answering
Audio-Visual Question Answering (AVQA)
+4
Human Keypoint Detection by Progressive Context Refinement
Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance of person instances.
Injecting Numerical Reasoning Skills into Knowledge Base Question Answering Models
Embedding-based methods are popular for Knowledge Base Question Answering (KBQA), but few current models have numerical reasoning skills and thus struggle to answer ordinal constrained questions.
Model Calibration in Dense Classification with Adaptive Label Perturbation
To improve model calibration, we propose Adaptive Stochastic Label Perturbation (ASLP) which learns a unique label perturbation level for each training image.
Automated Detection of Myopic Maculopathy in MMAC 2023: Achievements in Classification, Segmentation, and Spherical Equivalent Prediction
As for Task 3 (prediction of spherical equivalent), we have designed a deep regression model based on the data distribution of the dataset and employed an integration strategy to enhance the model's prediction accuracy.
Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System
The deep cascade structure and the combination rule enable the proposed \textit{ldcTree} to have a stronger distributed feature representation ability.
Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
Such supervision, while labor-intensive and not always possible, tends to hinder the generalization ability of the learned models.
Unsupervised Domain Adaptation: A Multi-task Learning-based Method
This paper presents a novel multi-task learning-based method for unsupervised domain adaptation.
Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
Specifically, we propose to randomly shuffle the pixels in the origin images and leverage the shuffled image as input to make CNN more concerned with the statistical properties.
Unfolding Hidden Barriers by Active Enhanced Sampling
We introduce an active learning scheme that consists of a parametric CV learner based on deep neural network and a CV-based enhanced sampler.
Deep Edge-Aware Saliency Detection
There has been profound progress in visual saliency thanks to the deep learning architectures, however, there still exist three major challenges that hinder the detection performance for scenes with complex compositions, multiple salient objects, and salient objects of diverse scales.
Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition: A Problem-Oriented Perspective
This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition.
Integrated Deep and Shallow Networks for Salient Object Detection
Then the results from deep FCNN and RBD are concatenated to feed into a shallow network to map the concatenated feature maps to saliency maps.
Joint Geometrical and Statistical Alignment for Visual Domain Adaptation
This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition.
Ranked #5 on
Domain Adaptation
on Office-Caltech
Nighttime Haze Removal with Illumination Correction
ii) Then it achieves a color-balance result by performing a color correction step after estimating the color characteristics of the incident light.
RGB-D-based Action Recognition Datasets: A Survey
Human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention since the first work reported in 2010.
Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences
The results show that our approach can achieve state-of-the-art results on the individual datasets and without dramatical performance degradation on the Combined Dataset.
Towards Practical Visual Search Engine within Elasticsearch
In this paper, we describe our end-to-end content-based image retrieval system built upon Elasticsearch, a well-known and popular textual search engine.
Robust Tracking via Weighted Online Extreme Learning Machine
Therefore, our tracking method can fully learn both of the target object and background information to enhance the tracking performance, and it is evaluated in 20 challenge image sequences with different attributes including illumination, occlusion, deformation, etc., which achieves better performance than several state-of-the-art methods in terms of effectiveness and robustness.
