Search Results for author:
Found 372 papers, 178 papers with code
Auto-Debias: Debiasing Masked Language Models with Automated Biased Prompts
Specifically, we propose a variant of the beam search method to automatically search for biased prompts such that the cloze-style completions are the most different with respect to different demographic groups.
Content-Consistent Matching for Domain Adaptive Semantic Segmentation
The target of CCM is to acquire those synthetic images that share similar distribution with the real ones in the target domain, so that the domain gap can be naturally alleviated by employing the content-consistent synthetic images for training.
Ranked #11 on
Semantic Segmentation
on GTAV-to-Cityscapes Labels
Benchmarking Intersectional Biases in NLP
While much work has highlighted biases embedded in state-of-the-art language models, and more recent efforts have focused on how to debias, research assessing the fairness and performance of biased/debiased models on downstream prediction tasks has been limited.
Learning Numeracy: A Simple Yet Effective Number Embedding Approach Using Knowledge Graph
Numeracy plays a key role in natural language understanding.
Constructing a Psychometric Testbed for Fair Natural Language Processing
We also discuss the important implications of our work and resulting testbed for future NLP research on psychometrics and fairness.
Buy Tesla, Sell Ford: Assessing Implicit Stock Market Preference in Pre-trained Language Models
Given the prevalence of NLP models in financial decision making systems, this work raises the awareness of their potential implicit preferences in the stock markets.
Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time
Moreover, on the seemingly implausible x16 interpolation task, our method outperforms existing methods by more than 1. 5 dB in terms of PSNR.
Sector Patch Embedding: An Embedding Module Conforming to The Distortion Pattern of Fisheye Image
And this fact leads to poor performance on some fisheye vision tasks.
CRRS: Concentric Rectangles Regression Strategy for Multi-point Representation on Fisheye Images
Compared with the previous work for muti-point representation, the experiments show that CRRS can improve the training performance both in accurate and stability.
Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation
However, using a single kind of modeling structure is difficult to balance the learning of short-term and long-term temporal correlations, and may bias the network to one of them, leading to undesirable predictions like global location shift, temporal inconsistency, and insufficient local details.
Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning
Specifically, DLL decouples the predicate labels and adopts separate classifiers to learn actional and spatial patterns respectively.
Decomposed Prototype Learning for Few-Shot Scene Graph Generation
To this end, we propose a novel Decomposed Prototype Learning (DPL).
Exploring Expression-related Self-supervised Learning for Affective Behaviour Analysis
This paper explores an expression-related self-supervised learning (SSL) method (ContraWarping) to perform expression classification in the 5th Affective Behavior Analysis in-the-wild (ABAW) competition.
Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation
The objective of this paper is self-supervised learning of video object segmentation.
Unsupervised Facial Expression Representation Learning with Contrastive Local Warping
Therefore, given a facial image, ContraWarping employs some global transformations and local warping to generate its positive and negative samples and sets up a novel contrastive learning framework.
Lana: A Language-Capable Navigator for Instruction Following and Generation
Recently, visual-language navigation (VLN) -- entailing robot agents to follow navigation instructions -- has shown great advance.
DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training
This decoder is both data-efficient and computation-efficient: 1) it only requires the text data for training, easing the burden on the collection of paired data.
Soft Prompt Guided Joint Learning for Cross-Domain Sentiment Analysis
Aspect term extraction is a fundamental task in fine-grained sentiment analysis, which aims at detecting customer's opinion targets from reviews on product or service.
Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding
To systematically benchmark the compositional generalizability of temporal grounding models, we introduce a new Compositional Temporal Grounding task and construct two new dataset splits, i. e., Charades-CG and ActivityNet-CG.
Temporal Perceiving Video-Language Pre-training
Specifically, text-video localization consists of moment retrieval, which predicts start and end boundaries in videos given the text description, and text localization which matches the subset of texts with the video features.
DR-WLC: Dimensionality Reduction cognition for object detection and pose estimation by Watching, Learning and Checking
For example, 2D object detection usually requires a large amount of 2D annotation data with high cost.
Analogical Inference Enhanced Knowledge Graph Embedding
And in AnKGE, we train an analogy function for each level of analogical inference with the original element embedding from a well-trained KGE model as input, which outputs the analogical object embedding.
Further Improving Weakly-supervised Object Localization via Causal Knowledge Distillation
Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels.
Knowledge Distillation
Weakly Supervised Object Localization
+1
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
In this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video Attribute Association mechanism, which leverages the Video-to-Text knowledge to generate textual auxiliary attributes for complementing video recognition.
Ranked #1 on
Action Recognition
on UCF101
StepNet: Spatial-temporal Part-aware Network for Sign Language Recognition
As the name implies, StepNet consists of two modules: Part-level Spatial Modeling and Part-level Temporal Modeling.
MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering
To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must.
One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation
In this paper, we propose Progressive Volume Distillation (PVD), a systematic distillation method that allows any-to-any conversions between different architectures, including MLP, sparse or low-rank tensors, hashtables and their compositions.
Ranked #1 on
Novel View Synthesis
on NeRF
(Average PSNR metric)
Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification
Second, we instantiate the loss function and provide a strong baseline for FGVC, where the performance of a naive backbone can be boosted and be comparable with recent methods.
Ranked #26 on
Fine-Grained Image Classification
on CUB-200-2011
Fine-Grained Image Classification
Fine-Grained Visual Recognition
A Light-weight, Effective and Efficient Model for Label Aggregation in Crowdsourcing
Due to the dynamic nature, the proposed algorithms can also estimate true labels online without re-visiting historical data.
Stereo Image Rain Removal via Dual-View Mutual Attention
Stereo images, containing left and right view images with disparity, are utilized in solving low-vision tasks recently, e. g., rain removal and super-resolution.
ReLER@ZJU Submission to the Ego4D Moment Queries Challenge 2022
Moreover, in order to better capture the long-term temporal dependencies in the long videos, we propose a segment-level recurrence mechanism.
Exploiting Contrastive Learning and Numerical Evidence for Improving Confusing Legal Judgment Prediction
Given the fact description text of a legal case, legal judgment prediction (LJP) aims to predict the case's charge, law article and penalty term.
PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
In an attempt to fill this gap, we propose a unified pixel- and patch-wise self-supervised learning framework, called PiPa, for domain adaptive semantic segmentation that facilitates intra-image pixel-wise correlations and patch-wise semantic consistency against different contexts.
Ranked #1 on
Semantic Segmentation
on SYNTHIA-to-Cityscapes
An Improved End-to-End Multi-Target Tracking Method Based on Transformer Self-Attention
This study proposes an improved end-to-end multi-target tracking algorithm that adapts to multi-view multi-scale scenes based on the self-attentive mechanism of the transformer's encoder-decoder structure.
Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization
Cross-view geo-localization aims to spot images of the same location shot from two platforms, e. g., the drone platform and the satellite platform.
DMRNet++: Learning Discriminative Features with Decoupled Networks and Enriched Pairs for One-Step Person Search
Person search aims at localizing and recognizing query persons from raw video frames, which is a combination of two sub-tasks, i. e., pedestrian detection and person re-identification.
Ranked #3 on
Person Search
on PRW
NoiSER: Noise is All You Need for Low-Light Image Enhancement
In this paper, we present an embarrassingly simple yet effective solution to a seemingly impossible mission, low-light image enhancement (LLIE) without access to any task-related data.
TAP-Vid: A Benchmark for Tracking Any Point in a Video
Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move.
Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning
We design Semantic Attention (SA) and generative Knowledge Disentanglement (KD) to learn the dependence of feasibility and contextuality, respectively.
Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in The Dark
Specifically, we present a decoupled interaction module (DIM) that aims for sufficient dual-view information interaction.
Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing
Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence (AI) for many years.
Tele-Knowledge Pre-training for Fault Analysis
In this work, we share our experience on tele-knowledge pre-training for fault analysis, a crucial task in telecommunication applications that requires a wide range of knowledge normally found in both machine log data and product documents.
Perception Test: A Diagnostic Benchmark for Multimodal Models
We propose a novel multimodal benchmark – the Perception Test – that aims to extensively evaluate perception and reasoning skills of multimodal models.
Swinv2-Imagen: Hierarchical Vision Transformer Diffusion Models for Text-to-Image Generation
Recently, diffusion models have been proven to perform remarkably well in text-to-image synthesis tasks in a number of studies, immediately presenting new study opportunities for image generation.
Ranked #1 on
Text-to-Image Generation
on Multi-Modal-CelebA-HQ
Decoupling Features in Hierarchical Propagation for Video Object Segmentation
To solve such a problem and further facilitate the learning of visual embeddings, this paper proposes a Decoupling Features in Hierarchical Propagation (DeAOT) approach.
Ranked #1 on
Semi-Supervised Video Object Segmentation
on MOSE
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
Feature-Proxy Transformer for Few-Shot Segmentation
With a rethink of recent advances, we find that the current FSS framework has deviated far from the supervised segmentation framework: Given the deep features, FSS methods typically use an intricate decoder to perform sophisticated pixel-wise matching, while the supervised segmentation methods use a simple linear classification head.
Sparse Teachers Can Be Dense with Knowledge
Recent advances in distilling pretrained language models have discovered that, besides the expressiveness of knowledge, the student-friendliness should be taken into consideration to realize a truly knowledgable teacher.
GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models
Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature, class).
Seeing Through the Noisy Dark: Towards Real-world Low-Light Image Enhancement and Denoising
Low-light image enhancement (LLIE) aims at improving the illumination and visibility of dark images with lighting noise.
Slimmable Networks for Contrastive Self-supervised Learning
One evidence of the interference is \emph{gradient imbalance}: a small proportion of parameters produces dominant gradients during backpropagation, and the main parameters may not be fully optimized.
Boost CTR Prediction for New Advertisements via Modeling Visual Content
To overcome the limitations of behavior ID features in modeling new ads, we exploit the visual content in ads to boost the performance of CTR prediction models.
Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising
How to pair the video ads with the user search is the core task of Baidu video advertising.
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation
To this end, we propose a novel model-agnostic Label Semantic Knowledge Distillation (LS-KD) for unbiased SGG.
Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation
In this work, we propose a new online VIS paradigm named Instance As Identity (IAI), which models temporal information for both detection and tracking in an efficient way.
GPPF: A General Perception Pre-training Framework via Sparsely Activated Multi-Task Learning
SIMT lays the foundation of pre-training with large-scale multi-task multi-domain datasets and is proved essential for stable training in our GPPF experiments.
Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation
However, we argue that most existing WSSGG works only focus on object-consistency, which means the grounded regions should have the same object category label as text entities.
NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation
To this end, we propose a novel NoIsy label CorrEction and Sample Training strategy for SGG: NICEST.
V$^2$L: Leveraging Vision and Vision-language Models into Large-scale Product Retrieval
While model ensemble is common, we show that combining the vision models and vision-language models brings particular benefits from their complementarity and is a key factor to our superiority.
Doge Tickets: Uncovering Domain-general Language Models by Playing Lottery Tickets
To uncover the domain-general LM, we propose to identify domain-general parameters by playing lottery tickets (dubbed doge tickets).
MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views
We propose MHR-Net, a novel method for recovering Non-Rigid Shapes from Motion (NRSfM).
Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation
We optimize the two losses and keypoint detector network in an end-to-end manner.
ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022
In this report, we present the ReLER@ZJU-Alibaba submission to the Ego4D Natural Language Queries (NLQ) Challenge in CVPR 2022.
Ranked #2 on
Natural Language Queries
on Ego4D
Data-Efficient Brain Connectome Analysis via Multi-Task Meta-Learning
Specifically, we propose to meta-train the model on datasets of large sample sizes and transfer the knowledge to small datasets.
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
Then, a spatial convolution is employed to capture the local structure of points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension.
A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection
Moreover, this paper further reveals a unique difficulty for solving the hard negative problem in ICD, i. e., there is a fundamental conflict between current metric learning and ICD.
Joint Representation Learning and Keypoint Detection for Cross-view Geo-localization
Inspired by the human visual system for mining local patterns, we propose a new framework called RK-Net to jointly learn the discriminative Representation and detect salient Keypoints with a single Network.
Ranked #2 on
Image-Based Localization
on cvusa
A Simple Yet Efficient Method for Adversarial Word-Substitute Attack
This research highlights that an adversary can fool a deep NLP model with much less cost.
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
In this paper, to reduce the number of redundant video tokens, we design a multi-segment token clustering algorithm to find the most representative tokens and drop the non-essential ones.
Ranked #8 on
Video Retrieval
on MSVD
(using extra training data)
3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective
This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image.
Ranked #1 on
Single-View 3D Reconstruction
on ATR
Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives
From the view of feature, we break down the video into trajectories and first leverage trajectory feature in VideoQA to enhance the alignment between two modalities.
Multiple-environment Self-adaptive Network for Aerial-view Geo-localization
This task is mostly regarded as an image retrieval problem.
FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring
Blind image deblurring (BID) remains a challenging and significant task.
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them.
Ranked #11 on
Domain Adaptation
on GTA5 to Cityscapes
Multi-View Consistent Generative Adversarial Networks for 3D-aware Image Synthesis
To address this challenge, we propose Multi-View Consistent Generative Adversarial Networks (MVCGAN) for high-quality 3D-aware image synthesis with geometry constraints.
In-N-Out Generative Learning for Dense Unsupervised Video Segmentation
By contrast, pixel-level optimization is more explicit, however, it is sensitive to the visual quality of training data and is not robust to object deformation.
Unified Transformer Tracker for Object Tracking
Although UniTrack \cite{wang2021different} demonstrates that a shared appearance model with multiple heads can be used to tackle individual tracking tasks, it fails to exploit the large-scale tracking datasets for training and performs poorly on single object tracking.
Automated Progressive Learning for Efficient Training of Vision Transformers
First, we develop a strong manual baseline for progressive learning of ViTs, by introducing momentum growth (MoGrow) to bridge the gap brought by model growth.
Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learning
Our target is to learn visual correspondence from unlabeled videos.
Deep Hierarchical Semantic Segmentation
In this paper, we instead address hierarchical semantic segmentation (HSS), which aims at structured, pixel-wise description of visual observation in terms of a class hierarchy.
Visual Abductive Reasoning
In this paper, we propose a new task and dataset, Visual Abductive Reasoning (VAR), for examining abductive reasoning ability of machine intelligence in everyday visual situations.
Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning
To systematically measure the compositional generalizability of temporal grounding models, we introduce a new Compositional Temporal Grounding task and construct two new dataset splits, i. e., Charades-CG and ActivityNet-CG.
Scalable Multi-object Identification for Video Object Segmentation
To match and segment multiple objects as efficiently as processing a single one, AOST employs an IDentification (ID) mechanism to assign objects with unique identities and associate them in a shared high-dimensional embedding space.
Semantic Segmentation
Semi-Supervised Video Object Segmentation
+1
Local-Global Context Aware Transformer for Language-Guided Video Segmentation
In light of this, we present Locater (local-global context aware Transformer), which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner.
Ranked #4 on
Referring Expression Segmentation
on A2D Sentences
Referring Expression Segmentation
Referring Video Object Segmentation
+4
Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains
Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer.
Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning
To deploy SSDR-AL in a more practical scenario, we design a noise-aware iterative labeling strategy to confront the "noisy annotation" problem introduced by the previous "dominant labeling" strategy in superpoints.
Results and findings of the 2021 Image Similarity Challenge
The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods.
COVID-19 Detection Using CT Image Based On YOLOv5 Network
The representational model are Faster RCNN and YOLO series.
Action Keypoint Network for Efficient Video Recognition
An effective approach is to select informative content from the holistic video, yielding a popular family of dynamic video recognition methods.
Ranked #36 on
Action Recognition
on Something-Something V1
Locality-Aware Inter- and Intra-Video Reconstruction for Self-Supervised Correspondence Learning
Our target is to learn visual correspondence from unlabeled videos.
Learning To Learn by Jointly Optimizing Neural Architecture and Weights
Existing NAS-based meta-learning methods apply a two-stage strategy, i. e., first searching architectures and then re-training meta-weights on the searched architecture.
Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images
The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data.
H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection
How to align the source and target domains is critical to the CDWSOD accuracy.
Ranked #1 on
Weakly Supervised Object Detection
on Clipart1k
Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification
These two unidirectional metrics (IR image to RGB proxy and RGB image to IR proxy) jointly alleviate the relay effect and benefit cross-modality association.
SEEG: Semantic Energized Co-Speech Gesture Generation
Talking gesture generation is a practical yet challenging task which aims to synthesize gestures in line with speech.
Ranked #5 on
Gesture Generation
on TED Gesture Dataset
A Simple Episodic Linear Probe Improves Visual Recognition in the Wild
In this paper, we propose an episodic linear probing (ELP) classifier to reflect the generalization of visual representations in an online manner.
Ranked #13 on
Fine-Grained Image Classification
on CUB-200-2011
Large-Scale Video Panoptic Segmentation in the Wild: A Benchmark
In contrast, our large-scale VIdeo Panoptic Segmentation in the Wild (VIPSeg) dataset provides 3, 536 videos and 84, 750 frames with pixel-level panoptic annotations, covering a wide range of real-world scenarios and categories.
PartialFed: Cross-Domain Personalized Federated Learning via Partial Initialization
The superiority of our algorithm is proved by demonstrating the new state-of-the-art results on cross-domain federated classification and detection.
Triggerless Backdoor Attack for NLP Tasks with Clean Labels
To deal with this issue, in this paper, we propose a new strategy to perform textual backdoor attacks which do not require an external trigger, and the poisoned samples are correctly labeled.
D$^2$LV: A Data-Driven and Local-Verification Approach for Image Copy Detection
In this paper, a data-driven and local-verification (D$^2$LV) approach is proposed to compete for Image Similarity Challenge: Matching Track at NeurIPS'21.
Bag of Tricks and A Strong baseline for Image Copy Detection
In this paper, a bag of tricks and a strong baseline are proposed for image copy detection.
Arch-Net: Model Distillation for Architecture Agnostic Model Deployment
For example, Transformer Networks do not have native support on many popular chips, and hence are difficult to deploy.
Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks
In the low-bit quantization field, training Binary Neural Networks (BNNs) is the extreme solution to ease the deployment of deep models on resource-constrained devices, having the lowest storage cost and significantly cheaper bit-wise operations compared to 32-bit floating-point counterparts.
Dynamic Slimmable Denoising Network
Here, we present dynamic slimmable denoising network (DDS-Net), a general method to achieve good denoising quality with less computational complexity, via dynamically adjusting the channel configurations of networks at test time with respect to different noisy images.
Active Learning for Deep Visual Tracking
In this paper, we propose an active learning method for deep visual tracking, which selects and annotates the unlabeled samples to train the deep CNNs model.
Contrastive Video-Language Segmentation
We focus on the problem of segmenting a certain object referred by a natural language sentence in video content, at the core of formulating a pinpoint vision-language relation.
Switch to Generalize: Domain-Switch Learning for Cross-Domain Few-Shot Classification
We hold a hypothesis, i. e., if a deep model is capable to fast generalize itself to different domains (using very few samples) during training, it will maintain such domain generalization capacity for testing.
Toward a Fairness-Aware Scoring System for Algorithmic Decision-Making
Then, we transform the social welfare maximization problem into the risk minimization task in machine learning, and derive a fairness-aware scoring system with the help of mixed integer programming.
Single-stream CNN with Learnable Architecture for Multi-source Remote Sensing Data
In the experiments, the proposed method is applied to ResNet and UNet, and the adjusted networks are verified on three very diverse benchmark data sets (i. e., Houston2018 data, Berlin data, and MUUFL data).
Weakly Supervised Person Search with Region Siamese Networks
Large-scale labeled training data is often difficult to collect, especially for person identities.
F3S: Free Flow Fever Screening
Identification of people with elevated body temperature can reduce or dramatically slow down the spread of infectious diseases like COVID-19.
Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes
Albeit simple, the pre-trained encoder can capture the key points of an unseen point cloud and surpasses the encoder trained from scratch on downstream tasks.
Ranked #33 on
3D Part Segmentation
on ShapeNet-Part
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
This work targets designing a principled and unified training-free framework for Neural Architecture Search (NAS), with high performance, low cost, and in-depth interpretation.
Generating Superpixels for High-resolution Images with Decoupled Patch Calibration
Superpixel segmentation has recently seen important progress benefiting from the advances in differentiable deep learning.
PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion
As NRSfM is a highly under-constrained problem, we propose two new pairwise regularization to further regularize the reconstruction.
Vector-Decomposed Disentanglement for Domain-Invariant Object Detection
Secondly, domain-specific representations are introduced as the differences between the input and domain-invariant representations.
Resisting Out-of-Distribution Data Problem in Perturbation of XAI
Besides, our solution also resolves a fundamental problem with the faithfulness indicator, a commonly used evaluation metric of XAI algorithms that appears to be sensitive to the OoD issue.
Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference
Secondly, we introduce semantic coherence learning to explicitly encourage the semantic coherence of the adaptive hierarchical graph network from three hierarchies.
Saying the Unseen: Video Descriptions via Dialog Agents
Current vision and language tasks usually take complete visual data (e. g., raw images or videos) as input, however, practical scenarios may often consist the situations where part of the visual information becomes inaccessible due to various reasons e. g., restricted view with fixed camera or intentional vision block for security concerns.
ReGO: Reference-Guided Outpainting for Scenery Image
We aim to tackle the challenging yet practical scenery image outpainting task in this work.
Removing Raindrops and Rain Streaks in One Go
First, we propose a complementary cascaded network architecture, namely CCN, to remove rain streaks and raindrops in a unified framework.
VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild
To the best of our knowledge, our VSPW is the first attempt to tackle the challenging video scene parsing task in the wild by considering diverse scenarios.
Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos
To capture the dynamics in point cloud videos, point tracking is usually employed.
Exploring Heterogeneous Clues for Weakly-Supervised Audio-Visual Video Parsing
Previous works take the overall event labels to supervise both audio and visual model predictions.
Graph-based Joint Pandemic Concern and Relation Extraction on Twitter
However, detecting concerns in time from massive information in social media turns out to be a big challenge, especially when sufficient manually labeled data is in the absence of public health emergencies, e. g., COVID-19.
Domain Consensus Clustering for Universal Domain Adaptation
To better exploit the intrinsic structure of the target domain, we propose Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and private ones.
Ranked #1 on
Universal Domain Adaptation
on Office-Home
Few-Shot Segmentation via Cycle-Consistent Transformer
Directly performing cross-attention may aggregate these features from support to query and bias the query features.
Ranked #35 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
Associating Objects with Transformers for Video Object Segmentation
The state-of-the-art methods learn to decode features with a single positive object and thus have to match and segment each target separately under multi-object scenarios, consuming multiple times computing resources.
Ranked #3 on
Semi-Supervised Video Object Segmentation
on MOSE
CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes
In this work, we describe our creation of a dataset of clinical action items annotated over MIMIC-III, the largest publicly available dataset of real clinical notes.
Less is More: Sparse Sampling for Dense Reaction Predictions
Obtaining viewer responses from videos can be useful for creators and streaming platforms to analyze the video performance and improve the future user experience.
Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation
Referring video object segmentation (RVOS) aims to segment video objects with the guidance of natural language reference.
One-shot visual object segmentation
Referring Video Object Segmentation
+2
Divide and Rule: Recurrent Partitioned Network for Dynamic Processes
Differently, our goal is to represent a system with a part-whole hierarchy and discover the implied dependencies among intra-system variables: inferring the interactions that possess causal effects on the sub-system behavior with REcurrent partItioned Network (REIN).
Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes
The hierarchical features help the model highlight the decision boundary and focus on hard pixels, and the structural information learned from base classes is treated as the prior knowledge for novel classes.
Connecting Language and Vision for Natural Language-Based Vehicle Retrieval
In this paper, we apply one new modality, i. e., the language description, to search the vehicle of interest and explore the potential of this task in the real-world scenario.
VidFace: A Full-Transformer Solver for Video FaceHallucination with Unaligned Tiny Snapshots
In this paper, we investigate the task of hallucinating an authentic high-resolution (HR) human face from multiple low-resolution (LR) video snapshots.
OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation
Specifically, we expect to approximate the real joint distribution over the partial observation and latent variables, thus infer the unseen targets respectively.
Faster Meta Update Strategy for Noise-Robust Deep Learning
It has been shown that deep neural networks are prone to overfitting on biased training data.
Improving Weakly-supervised Object Localization via Causal Intervention
The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels.
Weakly Supervised Object Localization
Weakly-Supervised Object Localization
T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval
Moreover, a global alignment method is proposed to provide a global cross-modal measurement that is complementary to the local perspective.
DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency
In the first step, the framework learns to segment objects from real and synthetic data in a weakly-supervised fashion, and the segmentation masks will act as a prior for pose estimation.
Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems
Existing goal-oriented dialogue datasets focus mainly on identifying slots and values.
Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
Domain adaptation is to transfer the shared knowledge learned from the source domain to a new environment, i. e., target domain.
ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation
Text-based video segmentation is a challenging task that segments out the natural language referred objects in videos.
Ranked #2 on
Referring Expression Segmentation
on A2D Sentences
(Precision@0.9 metric)
Decoupled Spatial Temporal Graphs for Generic Visual Grounding
Visual grounding is a long-lasting problem in vision-language understanding due to its diversity and complexity.
Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar
By iteratively updating the latent representations and our decoder, our DAP-FSR will be adapted to the target domain, thus achieving authentic and high-quality upsampled HR faces.
RL-CSDia: Representation Learning of Computer Science Diagrams
Another type of diagrams such as from Computer Science is composed of graphics containing complex topologies and relations, and research on this type of diagrams is still blank.
Look, Cast and Mold: Learning 3D Shape Manifold from Single-view Synthetic Data
To generalize the model towards a real scenario, we propose to fulfill several aspects: (1) Look: visually incorporate spatial structure from the single view to enhance the expressiveness of representation; (2) Cast: perceptually align the 2D image features to the 3D shape priors with cross-modal semantic contrastive mapping; (3) Mold: reconstruct stereo-shape of target by transforming embeddings into the desired manifold.
Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
To address the challenging task of instance-aware human part parsing, a new bottom-up regime is proposed to learn category-level human semantic segmentation as well as multi-person pose estimation in a joint and end-to-end manner.
Universal-Prototype Enhancing for Few-Shot Object Detection
Thus, we develop a new framework of few-shot object detection with universal prototypes ({FSOD}^{up}) that owns the merit of feature generalization towards novel objects.
Ranked #19 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search
Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework.
Ranked #7 on
Person Search
on PRW
Learning Audio-Visual Correlations from Variational Cross-Modal Generation
People can easily imagine the potential sound while seeing an event.
Search for Axion(-like) Particles in Heavy-Ion Collisions
We propose a novel way to search for axion(-like) particles in heavy-ion collisions using prompt photons as the probe and the property of conversion between photon and axion(-like) particles under a strong magnetic field generated in the non-central collisions.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Modeling the Probabilistic Distribution of Unlabeled Data forOne-shot Medical Image Segmentation
Thus, it is more desirable to employ only a few labeled data in pursuing high segmentation performance.