mlsanityData to 14 Oct 2026

Hierarchical Conditional Relation Networks for Video Question Answering

arXiv 2002.10698 ↗First posted 25 Feb 2020cs.CVcited by 163

Not on the map. Why?

Abstract (arXiv)

Video question answering (VideoQA) is challenging as it requires modeling capacity to distill dynamic visual artifacts and distant relations and to associate them with linguistic concepts. We introduce a general-purpose reusable neural unit called Conditional Relation Network (CRN) that serves as a building block to construct more sophisticated structures for representation and reasoning over video. CRN takes as input an array of tensorial objects and a conditioning feature, and computes an array of encoded output objects. Model building becomes a simple exercise of replication, rearrangement and stacking of these reusable units for diverse modalities and contextual information. This design thus supports high-order relational and multi-step reasoning. The resulting architecture for VideoQA is a CRN hierarchy whose branches represent sub-videos or clips, all sharing the same question as the contextual condition. Our evaluations on well-known datasets achieved new SoTA results, demonstrating the impact of building a general-purpose reasoning unit on complex domains such as VideoQA.

Key facts. Cited by 163 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 26; 2022: 46; 2023: 36; 2024: 34; 2025: 16; 2026: 5.

163 papers.

Sort:

By area:

  1. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  2. 2021NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actionscited by 744
  3. 2021Less is More: ClipBERT for Video-and-Language Learning via Sparse Samplingcited by 484
  4. 2022X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrievalcited by 280
  5. 2022Zero-Shot Video Question Answering via Frozen Bidirectional Language Modelscited by 229
  6. 2021Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptionscited by 226
  7. 2024STAR: A Benchmark for Situated Reasoning in Real-World Videoscited by 213
  8. 2022Learning to Answer Questions in Dynamic Audio-Visual Scenarioscited by 191
  9. 2021VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modelingcited by 188
  10. 2022All in One: Exploring Unified Video-Language Pre-trainingcited by 171
  11. 2021Align and Prompt: Video-and-Language Pre-training with Entity Promptscited by 149
  12. 2023EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbonecited by 130
38 more
  1. 2021AGQA: A Benchmark for Compositional Spatio-Temporal Reasoningcited by 120
  2. 2022EgoTaskQA: Understanding Human Tasks in Egocentric Videoscited by 115
  3. 2021VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluationcited by 95
  4. 2025EgoLife: Towards Egocentric Life Assistantcited by 91
  5. 2022CenterCLIP: Token Clustering for Efficient Text-Video Retrievalcited by 86
  6. 2021SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Eventscited by 84
  7. 2022Video Question Answering: Datasets, Algorithms and Challengescited by 84
  8. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 76
  9. 2022An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modelingcited by 74
  10. 2021Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoningcited by 68
  11. 2021Video as Conditional Graph Hierarchy for Multi-Granular Question Answeringcited by 68
  12. 2022Invariant Grounding for Video Question Answeringcited by 68
  13. 2022ComPhy: Compositional Physical Reasoning of Objects and Events from Videoscited by 63
  14. 2022Video Graph Transformer for Video Question Answeringcited by 63
  15. 2022Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answeringcited by 57
  16. 2021Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answeringcited by 56
  17. 2021Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Languagecited by 55
  18. 2022MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answeringcited by 55
  19. 2024CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarioscited by 53
  20. 2022From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answeringcited by 51
  21. 2024Context-Guided Spatio-Temporal Video Groundingcited by 46
  22. 2024Abductive Ego-View Accident Video Understanding for Safe Driving Perceptioncited by 43
  23. 2022Clover: Towards A Unified Video-Language Alignment and Fusion Modelcited by 41
  24. 2023Zero-Shot Video Question Answering with Procedural Programscited by 37
  25. 2024Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectivescited by 37
  26. 2021DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answeringcited by 35
  27. 2022Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Groundingcited by 35
  28. 2023Contrastive Video Question Answering via Video Graph Transformercited by 32
  29. 2022(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answeringcited by 30
  30. 2022Learning to Answer Visual Questions from Web Videoscited by 30
  31. 2021Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answeringcited by 29
  32. 2023Progressive Spatio-temporal Perception for Audio-Visual Question Answeringcited by 29
  33. 2024VideoQA in the Era of LLMs: An Empirical Studycited by 29
  34. 2023Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Modelscited by 27
  35. 2021Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answeringcited by 26
  36. 2022Exploring Motion and Appearance Information for Temporal Sentence Groundingcited by 24
  37. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  38. 2024CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Processcited by 23

50 most cited of 163 All 163 (JSON)