{"total":37,"rows":[{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2409.07825","title":"Deep Multimodal Learning with Missing Modality: A Survey","created":"2024-09-12","cited_by_count":92,"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":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","cited_by_count":66,"area":null},{"id":"2403.10380","title":"BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics","created":"2024-03-15","cited_by_count":36,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"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":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","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":"2404.05206","title":"SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2502.20361","title":"OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2307.04760","title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2310.00109","title":"FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","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":"2401.11470","title":"Exploring Missing Modality in Multimodal Egocentric Datasets","created":"2024-01-21","cited_by_count":7,"area":null},{"id":"2312.00055","title":"LEAP: LLM-Generation of Egocentric Action Programs","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2311.16446","title":"Centre Stage: Centricity-based Audio-Visual Temporal Action Detection","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2402.02889","title":"Exploring Federated Self-Supervised Learning for General Purpose Audio Understanding","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2407.08691","title":"ElasticAST: An Audio Spectrogram Transformer for All Length and Resolutions","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2411.17283","title":"BadScan: An Architectural Backdoor Attack on Visual State Space Models","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2503.13821","title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2504.09516","title":"FSSUAVL: A Discriminative Framework using Vision Models for Federated Self-Supervised Audio and Image Understanding","created":"2025-04-13","cited_by_count":1,"area":null},{"id":"2509.17641","title":"AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2605.02596","title":"HARMES: A Multi-Modal Dataset for Wearable Human Activity Recognition with Motion, Environmental Sensing and Sound","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2609.21183","title":"I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2306.08998","title":"Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2307.07265","title":"AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2412.05951","title":"When Vision Models Meet Parameter Efficient Look-Aside Adapters Without Large-Scale Audio Pretraining","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2503.23447","title":"CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition","created":"2025-03-30","cited_by_count":0,"area":null},{"id":"2505.20788","title":"Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic Dataset","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2506.10754","title":"BNMusic: Blending Environmental Noises into Personalized Music","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2511.13863","title":"Segmenting Collision Sound Sources in Egocentric Videos","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2512.07845","title":"AudioScene: Integrating Object-Event Audio into 3D Scenes","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2608.22359","title":"Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video","created":"2026-08-23","cited_by_count":0,"area":null}],"next_cursor":null}