CVPR

Language-Guided Audio-Visual Source Separation via Trimodal Consistency

Bias Mimicking: A Simple Sampling Approach for Bias Mitigation

Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval

MaskSketch: Unpaired Structure-guided Masked Image Generation

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

Understanding and Improving Visual Prompting: A Label-Mapping Perspective

Video Test-Time Adaptation for Action Recognition

Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models

SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer

FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer

Masked Motion Encoding for Self-Supervised Video Representation Learning

EC^2 : Emergent Communication for Embodied Control

Learning Situation Hyper-Graphs for Video Question Answering

Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos

Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners

3D Concept Learning and Reasoning from Multi-View Images

Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention

Teaching Structured Vision & Language Concepts to Vision & Language Models

CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning

Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition

Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions

Non-Adversarial Video Synthesis with Learned Priors

Camera On-boarding for Person Re-identification using Hypothesis Transfer Learning

Semi-Supervised Action Recognition with Temporal Contrastive Learning

Fashion IQ: A New Dataset towards Retrieving Images by Natural Language Feedback

GAN Compression: Efficient Architectures for Interactive Conditional GANs

Separating Skills and Concepts for Novel Visual Question Answering

Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

Fine-grained Angular Contrastive Learning with Coarse Labels

Black-box Explanation of Object Detectors via Saliency Maps

Anycost GANs for Interactive Image Synthesis and Editing

Relationship Matters: Relation Guided Knowledge Transfer for Incremental Learning of Object Detectors

Identifying Interpretable Action Concepts in Deep Networks

Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation