{"total":16,"rows":[{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2301.10939","title":"Affective Faces for Goal-Driven Dyadic Communication","created":"2023-01-26","cited_by_count":35,"area":null},{"id":"2109.03413","title":"YouRefIt: Embodied Reference Understanding with Language and Gesture","created":"2021-09-08","cited_by_count":33,"area":null},{"id":"2309.01073","title":"Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding","created":"2023-09-03","cited_by_count":11,"area":null},{"id":"2405.12621","title":"Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition","created":"2024-05-21","cited_by_count":10,"area":null},{"id":"2206.10665","title":"BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios","created":"2022-06-21","cited_by_count":8,"area":null},{"id":"2108.02846","title":"Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2405.11841","title":"Evaluating and Modeling Social Intelligence: A Comparative Study of Human and AI Capabilities","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2407.01548","title":"From Cognition to Computation: A Comparative Review of Human Attention and Transformer Architectures","created":"2024-04-25","cited_by_count":6,"area":null},{"id":"2407.06762","title":"Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions","created":"2024-07-09","cited_by_count":6,"area":null},{"id":"2508.12480","title":"The Yokai Learning Environment: Tracking Beliefs Over Space and Time","created":"2025-08-17","cited_by_count":3,"area":null},{"id":"2411.08451","title":"AD-DINO: Attention-Dynamic DINO for Distance-Aware Embodied Reference Understanding","created":"2024-11-13","cited_by_count":2,"area":null},{"id":"2305.12369","title":"HIINT: Historical, Intra- and Inter- personal Dynamics Modeling with Cross-person Memory Transformer","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2306.15253","title":"MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2511.15887","title":"Mind the Motions: Benchmarking Theory-of-Mind in Everyday Body Language","created":"2025-11-19","cited_by_count":1,"area":null}],"next_cursor":null}