{"total":213,"rows":[{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"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":"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":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232,"area":null},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2112.07642","title":"EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices","created":"2021-12-14","cited_by_count":139,"area":null},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114,"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":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85,"area":null},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67,"area":null},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66,"area":null},{"id":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64,"area":null},{"id":"2305.16487","title":"EgoHumans: An Egocentric 3D Multi-Human Benchmark","created":"2023-05-25","cited_by_count":60,"area":null},{"id":"2104.02026","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","created":"2021-04-05","cited_by_count":59,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50,"area":null},{"id":"2310.19795","title":"SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization","created":"2023-10-30","cited_by_count":48,"area":null},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46,"area":null},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46,"area":null},{"id":"2305.11019","title":"Annotation-free Audio-Visual Segmentation","created":"2023-05-18","cited_by_count":46,"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":"2406.01210","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","created":"2024-06-03","cited_by_count":44,"area":null},{"id":"2401.00789","title":"Retrieval-Augmented Egocentric Video Captioning","created":"2024-01-01","cited_by_count":42,"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":"2210.12649","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","created":"2022-10-23","cited_by_count":41,"area":null},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40,"area":null},{"id":"2303.04439","title":"A Light Weight Model for Active Speaker Detection","created":"2023-03-08","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":"2410.05352","title":"Recent Advances of Multimodal Continual Learning: A Comprehensive Survey","created":"2024-10-07","cited_by_count":39,"area":null},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37,"area":null},{"id":"2105.05165","title":"AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition","created":"2021-05-11","cited_by_count":36,"area":null},{"id":"2209.08691","title":"MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain","created":"2022-09-19","cited_by_count":36,"area":null},{"id":"2110.10101","title":"Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition","created":"2021-10-19","cited_by_count":35,"area":null},{"id":"2203.14240","title":"Audio-Adaptive Activity Recognition Across Video Domains","created":"2022-03-27","cited_by_count":35,"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":"2202.03007","title":"Learning Sound Localization Better From Semantically Similar Samples","created":"2022-02-07","cited_by_count":32,"area":null},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","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":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"area":null},{"id":"2403.11074","title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","created":"2024-03-17","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":"2301.03213","title":"EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset","created":"2023-01-09","cited_by_count":27,"area":null},{"id":"2301.10931","title":"Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning","created":"2023-01-26","cited_by_count":26,"area":null},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26,"area":null},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25,"area":null},{"id":"2301.08237","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","created":"2023-01-19","cited_by_count":25,"area":null},{"id":"2304.00387","title":"HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions","created":"2023-04-01","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"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":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23,"area":null},{"id":"2209.13583","title":"Learning State-Aware Visual Representations from Audible Interactions","created":"2022-09-27","cited_by_count":23,"area":null},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","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":"2106.14118","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","created":"2021-06-27","cited_by_count":21,"area":null},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21,"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":"2406.09272","title":"Action2Sound: Ambient-Aware Generation of Action Sounds from Egocentric Videos","created":"2024-06-13","cited_by_count":21,"area":null},{"id":"2203.02216","title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","created":"2022-03-04","cited_by_count":20,"area":null},{"id":"2206.09852","title":"M&M Mix: A Multimodal Multiview Transformer Ensemble","created":"2022-06-20","cited_by_count":20,"area":null},{"id":"2206.12714","title":"Defending Multimodal Fusion Models against Single-Source Adversaries","created":"2022-06-25","cited_by_count":20,"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":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2308.12558","title":"Hyperbolic Audio-visual Zero-shot Learning","created":"2023-08-24","cited_by_count":19,"area":null},{"id":"2112.07787","title":"Revisiting 3D Object Detection From an Egocentric Perspective","created":"2021-12-14","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":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17,"area":null},{"id":"2312.04117","title":"Instance Tracking in 3D Scenes from Egocentric Videos","created":"2023-12-07","cited_by_count":17,"area":null},{"id":"2403.09805","title":"On the Utility of 3D Hand Poses for Action Recognition","created":"2024-03-14","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":"2404.01891","title":"ASTRA: An Action Spotting TRAnsformer for Soccer Videos","created":"2024-04-02","cited_by_count":16,"area":null},{"id":"2407.01518","title":"Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervision","created":"2024-07-01","cited_by_count":16,"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":"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":"2204.04734","title":"A Comparative Analysis of Decision-Level Fusion for Multimodal Driver Behaviour Understanding","created":"2022-04-10","cited_by_count":14,"area":null},{"id":"2305.15699","title":"Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective","created":"2023-05-25","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":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","cited_by_count":14,"area":null},{"id":"2208.02080","title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval","created":"2022-08-03","cited_by_count":13,"area":null},{"id":"2307.16617","title":"FULLER: Unified Multi-modality Multi-task 3D Perception via Multi-level Gradient Calibration","created":"2023-07-31","cited_by_count":13,"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":"2306.12795","title":"Learning Unseen Modality Interaction","created":"2023-06-22","cited_by_count":12,"area":null},{"id":"2501.13924","title":"Towards Robust Multimodal Open-set Test-time Adaptation via Adaptive Entropy-aware Optimization","created":"2025-01-23","cited_by_count":12,"area":null},{"id":"2307.02041","title":"Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing","created":"2023-07-05","cited_by_count":11,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2404.05206","title":"SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2111.05526","title":"Space-Time Memory Network for Sounding Object Localization in Videos","created":"2021-11-10","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}],"next_cursor":"100"}