{"total":25,"rows":[{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"area":null},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102,"area":null},{"id":"2110.06915","title":"Object-Region Video Transformers","created":"2021-10-13","cited_by_count":73,"area":null},{"id":"2111.09297","title":"Learning to Compose Visual Relations","created":"2021-11-17","cited_by_count":72,"area":null},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71,"area":null},{"id":"2406.08656","title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","created":"2024-06-12","cited_by_count":43,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2202.09277","title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","created":"2022-02-18","cited_by_count":30,"area":null},{"id":"2111.08960","title":"Compositional Transformers for Scene Generation","created":"2021-11-17","cited_by_count":24,"area":null},{"id":"2212.04821","title":"PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data","created":"2022-12-08","cited_by_count":14,"area":null},{"id":"2410.17751","title":"VISAGE: Video Synthesis using Action Graphs for Surgery","created":"2024-10-23","cited_by_count":11,"area":null},{"id":"2403.04899","title":"Towards Scene Graph Anticipation","created":"2024-03-07","cited_by_count":10,"area":null},{"id":"2211.06119","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","created":"2022-11-11","cited_by_count":8,"area":null},{"id":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2211.14308","title":"WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2211.14309","title":"FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations","created":"2022-11-25","cited_by_count":5,"area":null},{"id":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2304.07483","title":"Video Generation Beyond a Single Clip","created":"2023-04-15","cited_by_count":3,"area":null},{"id":"2307.03538","title":"Language-free Compositional Action Generation via Decoupling Refinement","created":"2023-07-07","cited_by_count":2,"area":null},{"id":"2206.06346","title":"Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens","created":"2022-06-13","cited_by_count":0,"area":null},{"id":"2406.10469","title":"Object-Attribute-Relation Representation Based Video Semantic Communication","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2409.00295","title":"Box2Flow: Instance-based Action Flow Graphs from Videos","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2511.00107","title":"AI Powered High Quality Text to Video Generation with Enhanced Temporal Consistency","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2607.21580","title":"GraphVid: Interactive Graph-Controllable Video Generation","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}