{"total":21,"rows":[{"id":"2307.10616","title":"Heterogeneous Federated Learning: State-of-the-art and Research Challenges","created":"2023-07-20","cited_by_count":161,"area":null},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","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":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2104.07767","title":"Exploring Visual Engagement Signals for Representation Learning","created":"2021-04-15","cited_by_count":12,"area":null},{"id":"2203.14456","title":"3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos","created":"2022-03-28","cited_by_count":8,"area":null},{"id":"2109.02747","title":"WhyAct: Identifying Action Reasons in Lifestyle Vlogs","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2507.22934","title":"Deep Learning Approaches for Multimodal Intent Recognition: A Survey","created":"2025-07-24","cited_by_count":6,"area":null},{"id":"2209.00495","title":"Searching for Structure in Unfalsifiable Claims","created":"2022-08-19","cited_by_count":4,"area":null},{"id":"2308.10562","title":"Seeing the Intangible: Survey of Image Classification into High-Level and Abstract Categories","created":"2023-08-21","cited_by_count":4,"area":null},{"id":"2409.16736","title":"Commonly Interesting Images","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2109.02734","title":"Detecting Inspiring Content on Social Media","created":"2021-09-06","cited_by_count":2,"area":null},{"id":"2405.08427","title":"Impact of Stickers on Multimodal Sentiment and Intent in Social Media: A New Task, Dataset and Baseline","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2402.19339","title":"Stitching Gaps: Fusing Situated Perceptual Knowledge with Vision Transformers for High-Level Image Classification","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2504.18201","title":"Multi-Grained Compositional Visual Clue Learning for Image Intent Recognition","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2605.06832","title":"IntentGrasp: A Comprehensive Benchmark for Intent Understanding","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2511.23287","title":"Transformer-Driven Triple Fusion Framework for Enhanced Multimodal Author Intent Classification in Low-Resource Bangla","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2604.21786","title":"From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.12856","title":"Moltbook Moderation: Uncovering Hidden Intent Through Multi-Turn Dialogue","created":"2026-05-13","cited_by_count":0,"area":null}],"next_cursor":null}