mlsanityData to 7 Oct 2026

Temporal RoI Align for Video Object Recognition

arXiv 2109.03495 ↗First posted 8 Sep 2021cs.CVcited by 44

Not on the map. Why?

Abstract (arXiv)

Video object detection is challenging in the presence of appearance deterioration in certain video frames. Therefore, it is a natural choice to aggregate temporal information from other frames of the same video into the current frame. However, RoI Align, as one of the most core procedures of video detectors, still remains extracting features from a single-frame feature map for proposals, making the extracted RoI features lack temporal information from videos. In this work, considering the features of the same object instance are highly similar among frames in a video, a novel Temporal RoI Align operator is proposed to extract features from other frames feature maps for current frame proposals by utilizing feature similarity. The proposed Temporal RoI Align operator can extract temporal information from the entire video for proposals. We integrate it into single-frame video detectors and other state-of-the-art video detectors, and conduct quantitative experiments to demonstrate that the proposed Temporal RoI Align operator can consistently and significantly boost the performance. Besides, the proposed Temporal RoI Align can also be applied into video instance segmentation. Codes are available at https://github.com/open-mmlab/mmtracking

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 33 of its 38 references that are in the map. First posted on arXiv 8 Sep 2021.

Builds on

33 of 38 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2017Mask R-CNNcited by 7,259
  6. 2015Fast R-CNNcited by 2,930
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  10. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  11. 2017Deformable Convolutional Networkscited by 1,481
  12. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
21 more
  1. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  2. 2018Scaling Egocentric Vision: The EPIC-KITCHENS Datasetcited by 789
  3. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  4. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  5. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  6. 2019Video Instance Segmentationcited by 391
  7. 2017Relation Networks for Object Detectioncited by 305
  8. 2016Deep Feature Flow for Video Recognitioncited by 186
  9. 2017Flow-Guided Feature Aggregation for Video Object Detectioncited by 177
  10. 2017Detect to Track and Track to Detectcited by 131
  11. 2020Memory Enhanced Global-Local Aggregation for Video Object Detectioncited by 128
  12. 2019Sequence Level Semantics Aggregation for Video Object Detectioncited by 87
  13. 2019Relation Distillation Networks for Video Object Detectioncited by 77
  14. 2016Seq-NMS for Video Object Detectioncited by 68
  15. 2017Towards High Performance Video Object Detectioncited by 60
  16. 2018Object Detection in Video with Spatiotemporal Sampling Networkscited by 57
  17. 2017Video Object Detection with an Aligned Spatial-Temporal Memorycited by 41
  18. 2017Mobile Video Object Detection with Temporally-Aware Feature Mapscited by 39
  19. 2019Progressive Sparse Local Attention for Video object detectioncited by 30
  20. 2018Optimizing Video Object Detection via a Scale-Time Latticecited by 25
  21. 2018Learning Region Features for Object Detectioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 13; 2024: 10; 2025: 8; 2026: 6.

44 papers.

Sort:

  1. 2022TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 78
  2. 2023Learning Object State Changes in Videos: An Open-World Perspectivecited by 36
  3. 2022A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videoscited by 32
  4. 2023FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Visioncited by 22
  5. 2022YOLOV: Making Still Image Object Detectors Great at Video Object Detectioncited by 18
  6. 2022PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detectioncited by 17
  7. 2021Hybrid Instance-aware Temporal Fusion for Online Video Instance Segmentationcited by 13
  8. 2023FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectorscited by 10
  9. 2023Objects do not disappear: Video object detection by single-frame object location anticipationcited by 7
  10. 2022BoxMask: Revisiting Bounding Box Supervision for Video Object Detectioncited by 6
  11. 2022DFA: Dynamic Feature Aggregation for Efficient Video Object Detectioncited by 5
  12. 2023Flying Bird Object Detection Algorithm in Surveillance Video Based on Motion Informationcited by 5
32 more
  1. 2023DarkVision: A Benchmark for Low-light Image/Video Perceptioncited by 5
  2. 2023Learned Scalable Video Coding For Humans and Machinescited by 5
  3. 2023A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videoscited by 5
  4. 2024Practical Video Object Detection via Feature Selection and Aggregationcited by 5
  5. 2024FBD-SV-2024: Flying Bird Object Detection Dataset in Surveillance Videocited by 5
  6. 2025OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cookingcited by 5
  7. 2023Memory Maps for Video Object Detection and Tracking on UAVscited by 4
  8. 2023Traffic Video Object Detection using Motion Priorcited by 4
  9. 2024Mixture of Scale Experts for Alignment-free RGBT Video Object Detection and A Unified Benchmarkcited by 4
  10. 2023Erasure-based Interaction Network for RGBT Video Object Detection and A Unified Benchmarkcited by 3
  11. 2024A Flying Bird Object Detection Method for Surveillance Videocited by 3
  12. 2024XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videoscited by 3
  13. 2023SSVOD: Semi-Supervised Video Object Detection with Sparse Annotationscited by 2
  14. 2024Source-free Domain Adaptation for Video Object Detection Under Adverse Image Conditionscited by 2
  15. 2024A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shotcited by 2
  16. 2025Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cookingcited by 2
  17. 2023Object Detection Difficulty: Suppressing Over-aggregation for Faster and Better Video Object Detectioncited by 1
  18. 2024FlightScope: An Experimental Comparative Review of Aircraft Detection Algorithms in Satellite Imagerycited by 1
  19. 2024SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Drivingcited by 1
  20. 2024Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detectioncited by 1
  21. 2025Gaseous Object Detectioncited by 1
  22. 2025Spatiotemporal Learning with Context-aware Video Tubelets for Ultrasound Video Analysiscited by 0
  23. 2025Multimodal Spatio-temporal Graph Learning for Alignment-free RGBT Video Object Detectioncited by 0
  24. 2025A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applicationscited by 0
  25. 2025Contrastive Learning through Auxiliary Branch for Video Object Detectioncited by 0
  26. 2025Integrating Object Interaction Self-Attention and GAN-Based Debiasing for Visual Question Answeringcited by 0
  27. 2026BLO-Inst: Bi-Level Optimization Based Alignment of YOLO and SAM for Robust Instance Segmentationcited by 0
  28. 2026A multi-center analysis of deep learning methods for video polyp detection and segmentationcited by 0
  29. 2026Learn Temporal Consistency For Robust Satellite Video Detectorcited by 0
  30. 2026Multi-view feature High-order Fusion for Space Weak Object Detection and Segmentationcited by 0
  31. 2026Decoupled Motion Representation Learning for Moving Infrared Small Target Detectioncited by 0
  32. 2026Dual-Correlation Hypergraph Network for Unaligned RGBT Video Object Detection and A Large-scale Benchmarkcited by 0