{"total":135,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622,"area":null},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361,"area":null},{"id":"2203.15332","title":"Balanced Multimodal Learning via On-the-fly Gradient Modulation","created":"2022-03-29","cited_by_count":264,"area":null},{"id":"2104.13586","title":"Revisiting Skeleton-based Action Recognition","created":"2021-04-28","cited_by_count":257,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146,"area":null},{"id":"2211.07089","title":"PMR: Prototypical Modal Rebalance for Multimodal Learning","created":"2022-11-14","cited_by_count":116,"area":null},{"id":"2104.07905","title":"Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos","created":"2021-04-16","cited_by_count":99,"area":null},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98,"area":null},{"id":"2112.04446","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","created":"2021-12-08","cited_by_count":79,"area":null},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2103.03516","title":"Slow-Fast Auditory Streams For Audio Recognition","created":"2021-03-05","cited_by_count":56,"area":null},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54,"area":null},{"id":"2305.01233","title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning","created":"2023-05-02","cited_by_count":53,"area":null},{"id":"2102.02751","title":"Semi-Supervised Action Recognition with Temporal Contrastive Learning","created":"2021-02-04","cited_by_count":50,"area":null},{"id":"2404.18947","title":"Multimodal Fusion on Low-quality Data: A Comprehensive Survey","created":"2024-04-27","cited_by_count":49,"area":null},{"id":"2206.12772","title":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation","created":"2022-06-26","cited_by_count":44,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2111.01024","title":"With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition","created":"2021-11-01","cited_by_count":41,"area":null},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"area":null},{"id":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40,"area":null},{"id":"2104.13537","title":"Shot Contrastive Self-Supervised Learning for Scene Boundary Detection","created":"2021-04-28","cited_by_count":35,"area":null},{"id":"2104.00862","title":"Self-supervised Video Representation Learning by Context and Motion Decoupling","created":"2021-04-02","cited_by_count":34,"area":null},{"id":"2104.00682","title":"Multiview Pseudo-Labeling for Semi-supervised Learning from Video","created":"2021-04-01","cited_by_count":32,"area":null},{"id":"2111.09887","title":"PyTorchVideo: A Deep Learning Library for Video Understanding","created":"2021-11-18","cited_by_count":32,"area":null},{"id":"2202.03007","title":"Learning Sound Localization Better From Semantically Similar Samples","created":"2022-02-07","cited_by_count":32,"area":null},{"id":"2410.11582","title":"On-the-fly Modulation for Balanced Multimodal Learning","created":"2024-10-15","cited_by_count":32,"area":null},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2201.01928","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2203.03598","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2104.02000","title":"Can audio-visual integration strengthen robustness under multimodal attacks?","created":"2021-04-05","cited_by_count":23,"area":null},{"id":"2212.04638","title":"FLAG3D: A 3D Fitness Activity Dataset with Language Instruction","created":"2022-12-09","cited_by_count":23,"area":null},{"id":"2201.11095","title":"Self-attention fusion for audiovisual emotion recognition with incomplete data","created":"2022-01-26","cited_by_count":22,"area":null},{"id":"2207.07646","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","created":"2022-07-15","cited_by_count":22,"area":null},{"id":"2305.19458","title":"A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition","created":"2023-05-30","cited_by_count":21,"area":null},{"id":"2305.03907","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","created":"2023-05-06","cited_by_count":20,"area":null},{"id":"2402.09444","title":"Multimodal Action Quality Assessment","created":"2024-01-31","cited_by_count":20,"area":null},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2407.06628","title":"Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition","created":"2024-07-09","cited_by_count":18,"area":null},{"id":"2105.01646","title":"Motion-Augmented Self-Training for Video Recognition at Smaller Scale","created":"2021-05-04","cited_by_count":17,"area":null},{"id":"2111.05846","title":"Structure from Silence: Learning Scene Structure from Ambient Sound","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2211.01966","title":"MarginNCE: Robust Sound Localization with a Negative Margin","created":"2022-11-03","cited_by_count":16,"area":null},{"id":"2303.10757","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","created":"2023-03-19","cited_by_count":16,"area":null},{"id":"2303.16541","title":"Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation","created":"2023-03-29","cited_by_count":15,"area":null},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2411.07335","title":"Balancing Multimodal Training Through Game-Theoretic Regularization","created":"2024-11-11","cited_by_count":15,"area":null},{"id":"2203.03014","title":"Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2306.00595","title":"Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2312.12870","title":"The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective","created":"2023-12-20","cited_by_count":14,"area":null},{"id":"2503.18223","title":"MammAlps: A multi-view video behavior monitoring dataset of wild mammals in the Swiss Alps","created":"2025-03-23","cited_by_count":14,"area":null},{"id":"2507.13364","title":"OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning","created":"2025-07-06","cited_by_count":14,"area":null},{"id":"2104.00616","title":"Composable Augmentation Encoding for Video Representation Learning","created":"2021-04-01","cited_by_count":13,"area":null},{"id":"2107.00239","title":"Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)","created":"2021-07-01","cited_by_count":13,"area":null},{"id":"2301.09595","title":"Zorro: the masked multimodal transformer","created":"2023-01-23","cited_by_count":13,"area":null},{"id":"2308.13077","title":"Preserving Modality Structure Improves Multi-Modal Learning","created":"2023-08-24","cited_by_count":13,"area":null},{"id":"2206.15085","title":"Skeleton-based Action Recognition via Adaptive Cross-Form Learning","created":"2022-06-30","cited_by_count":12,"area":null},{"id":"2207.10664","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2303.17285","title":"Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection","created":"2023-03-30","cited_by_count":12,"area":null},{"id":"2104.01198","title":"Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories","created":"2021-04-02","cited_by_count":11,"area":null},{"id":"2106.09703","title":"MaCLR: Motion-aware Contrastive Learning of Representations for Videos","created":"2021-06-17","cited_by_count":10,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2206.03666","title":"Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking","created":"2022-06-08","cited_by_count":9,"area":null},{"id":"2506.09445","title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2508.08237","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2106.06736","title":"Multi-level Attention Fusion Network for Audio-visual Event Recognition","created":"2021-06-12","cited_by_count":7,"area":null},{"id":"2109.12065","title":"DeepStroke: An Efficient Stroke Screening Framework for Emergency Rooms with Multimodal Adversarial Deep Learning","created":"2021-09-24","cited_by_count":7,"area":null},{"id":"2301.00986","title":"Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition","created":"2023-01-03","cited_by_count":7,"area":null},{"id":"2401.11470","title":"Exploring Missing Modality in Multimodal Egocentric Datasets","created":"2024-01-21","cited_by_count":7,"area":null},{"id":"2104.05418","title":"Contrastive Learning of Global-Local Video Representations","created":"2021-04-07","cited_by_count":6,"area":null},{"id":"2109.08867","title":"V-SlowFast Network for Efficient Visual Sound Separation","created":"2021-09-18","cited_by_count":6,"area":null},{"id":"2311.06285","title":"Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2401.00403","title":"Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection","created":"2023-12-31","cited_by_count":6,"area":null},{"id":"2106.06939","title":"Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning","created":"2021-06-13","cited_by_count":5,"area":null},{"id":"2406.02554","title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","created":"2024-03-22","cited_by_count":5,"area":null},{"id":"2407.18552","title":"Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention","created":"2024-07-26","cited_by_count":5,"area":null},{"id":"2106.08323","title":"VidHarm: A Clip Based Dataset for Harmful Content Detection","created":"2021-06-15","cited_by_count":4,"area":null},{"id":"2202.04947","title":"OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos","created":"2022-02-10","cited_by_count":4,"area":null},{"id":"2208.09414","title":"ModSelect: Automatic Modality Selection for Synthetic-to-Real Domain Generalization","created":"2022-08-19","cited_by_count":4,"area":null},{"id":"2308.09322","title":"Audio-Visual Glance Network for Efficient Video Recognition","created":"2023-08-18","cited_by_count":4,"area":null},{"id":"2401.04023","title":"Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2106.03162","title":"Transformed ROIs for Capturing Visual Transformations in Videos","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2505.12903","title":"Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2104.09760","title":"HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition","created":"2021-04-20","cited_by_count":2,"area":null},{"id":"2207.08024","title":"LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2212.04700","title":"Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation","created":"2022-12-09","cited_by_count":2,"area":null},{"id":"2309.04579","title":"EGOFALLS: A visual-audio dataset and benchmark for fall detection using egocentric cameras","created":"2023-09-08","cited_by_count":2,"area":null},{"id":"2409.09678","title":"A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2501.01470","title":"Balance-aware Sequence Sampling Makes Multi-modal Learning Better","created":"2025-01-01","cited_by_count":2,"area":null},{"id":"2507.11967","title":"Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2507.21945","title":"Attention-Driven Multimodal Alignment for Long-term Action Quality Assessment","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2105.01517","title":"Where and When: Space-Time Attention for Audio-Visual Explanations","created":"2021-05-04","cited_by_count":1,"area":null}],"next_cursor":"100"}