mlsanityData to 7 Oct 2026

Video Relation Detection via Tracklet based Visual Transformer

arXiv 2108.08669 ↗First posted 19 Aug 2021cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Video Visual Relation Detection (VidVRD), has received significant attention of our community over recent years. In this paper, we apply the state-of-the-art video object tracklet detection pipeline MEGA and deepSORT to generate tracklet proposals. Then we perform VidVRD in a tracklet-based manner without any pre-cutting operations. Specifically, we design a tracklet-based visual Transformer. It contains a temporal-aware decoder which performs feature interactions between the tracklets and learnable predicate query embeddings, and finally predicts the relations. Experimental results strongly demonstrate the superiority of our method, which outperforms other methods by a large margin on the Video Relation Understanding (VRU) Grand Challenge in ACM Multimedia 2021. Codes are released at https://github.com/Dawn-LX/VidVRD-tracklets.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

21 of 33 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2016Layer Normalizationcited by 5,579
  9. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  11. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  12. 2020ResNeSt: Split-Attention Networkscited by 445
9 more
  1. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  2. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
  3. 2017Flow-Guided Feature Aggregation for Video Object Detectioncited by 177
  4. 2017Single-Shot Refinement Neural Network for Object Detectioncited by 129
  5. 2020Memory Enhanced Global-Local Aggregation for Video Object Detectioncited by 128
  6. 2016Seq-NMS for Video Object Detectioncited by 68
  7. 2018Counterfactual Critic Multi-Agent Training for Scene Graph Generationcited by 53
  8. 2019Video Relationship Reasoning using Gated Spatio-Temporal Energy Graphcited by 41
  9. 2021Video Relation Detection with Trajectory-aware Multi-modal Featurescited by 8

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 4; 2023: 4; 2024: 3; 2025: 2.

17 papers.

Sort:

By area:

  1. 2021On Pursuit of Designing Multi-modal Transformer for Video Groundingcited by 54
  2. 2021Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphscited by 30
  3. 2021Natural Language Video Localization with Learnable Moment Proposalscited by 27
  4. 2021Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphscited by 23
  5. 2023Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detectioncited by 22
  6. 2022Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generationcited by 20
  7. 2023DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Drivingcited by 12
  8. 2023DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Groundingcited by 11
  9. 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
  10. 2022Rethinking the Evaluation of Unbiased Scene Graph Generationcited by 9
  11. 2022Video Event Extraction via Tracking Visual States of Argumentscited by 8
  12. 2025Event Extraction in Large Language Modelcited by 5
5 more
  1. 2025TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferringcited by 3
  2. 2023Open-Vocabulary Video Relation Extractioncited by 1
  3. 2024TD^2-Net: Toward Denoising and Debiasing for Dynamic Scene Graph Generationcited by 1
  4. 2024Video Relationship Detection Using Mixture of Expertscited by 1
  5. 2022Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectivescited by 0