mlsanityData to 7 Oct 2026

Salient Object Detection in RGB-D Videos

arXiv 2310.15482 ↗First posted 24 Oct 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Given the widespread adoption of depth-sensing acquisition devices, RGB-D videos and related data/media have gained considerable traction in various aspects of daily life. Consequently, conducting salient object detection (SOD) in RGB-D videos presents a highly promising and evolving avenue. Despite the potential of this area, SOD in RGB-D videos remains somewhat under-explored, with RGB-D SOD and video SOD (VSOD) traditionally studied in isolation. To explore this emerging field, this paper makes two primary contributions: the dataset and the model. On one front, we construct the RDVS dataset, a new RGB-D VSOD dataset with realistic depth and characterized by its diversity of scenes and rigorous frame-by-frame annotations. We validate the dataset through comprehensive attribute and object-oriented analyses, and provide training and testing splits. Moreover, we introduce DCTNet+, a three-stream network tailored for RGB-D VSOD, with an emphasis on RGB modality and treats depth and optical flow as auxiliary modalities. In pursuit of effective feature enhancement, refinement, and fusion for precise final prediction, we propose two modules: the multi-modal attention module (MAM) and the refinement fusion module (RFM). To enhance interaction and fusion within RFM, we design a universal interaction module (UIM) and then integrate holistic multi-modal attentive paths (HMAPs) for refining multi-modal low-level features before reaching RFMs. Comprehensive experiments, conducted on pseudo RGB-D video datasets alongside our RDVS, highlight the superiority of DCTNet+ over 17 VSOD models and 14 RGB-D SOD models. Ablation experiments were performed on both pseudo and realistic RGB-D video datasets to demonstrate the advantages of individual modules as well as the necessity of introducing realistic depth. Our code together with RDVS dataset will be available at https://github.com/kerenfu/RDVS/.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 49 of its 100 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

49 of 100 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  9. 2017Non-local Neural Networkscited by 2,290
  10. 2021Vision Transformers for Dense Predictioncited by 1,789
  11. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  12. 2017Structure-measure: A New Way to Evaluate Foreground Mapscited by 480
37 more
  1. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  2. 2014The Secrets of Salient Object Segmentationcited by 200
  3. 2019Salient Object Detection in the Deep Learning Era: An In-Depth Surveycited by 163
  4. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 142
  5. 2019Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarkscited by 133
  6. 2015Salient Object Detection: A Benchmarkcited by 130
  7. 2020JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detectioncited by 79
  8. 2021Full-Duplex Strategy for Video Object Segmentationcited by 78
  9. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  10. 2020RGB-D Salient Object Detection: A Surveycited by 73
  11. 2019Motion Guided Attention for Video Salient Object Detectioncited by 72
  12. 2020Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detectioncited by 72
  13. 2021Specificity-preserving RGB-D Saliency Detectioncited by 70
  14. 2020A Single Stream Network for Robust and Real-time RGB-D Salient Object Detectioncited by 67
  15. 2020Siamese Network for RGB-D Salient Object Detection and Beyondcited by 67
  16. 2021CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detectioncited by 47
  17. 2016RGBD Salient Object Detection via Deep Fusioncited by 46
  18. 2017Video Salient Object Detection via Fully Convolutional Networkscited by 46
  19. 2020DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detectioncited by 45
  20. 2021TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Networkcited by 45
  21. 2020Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detectioncited by 38
  22. 2022CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detectioncited by 38
  23. 2021Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detectioncited by 33
  24. 2019Adaptive Fusion for RGB-D Salient Object Detectioncited by 29
  25. 2023HRTransNet: HRFormer-Driven Two-Modality Salient Object Detectioncited by 27
  26. 2020TENet: Triple Excitation Network for Video Salient Object Detectioncited by 26
  27. 2020MobileSal: Extremely Efficient RGB-D Salient Object Detectioncited by 25
  28. 2023Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detectioncited by 25
  29. 2018PDNet: Prior-model Guided Depth-enhanced Network for Salient Object Detectioncited by 21
  30. 2016A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detectioncited by 19
  31. 2021BTS-Net: Bi-directional Transfer-and-Selection Network For RGB-D Salient Object Detectioncited by 15
  32. 2022A Survey on RGB-D Datasetscited by 11
  33. 2016Learning Gaze Transitions from Depth to Improve Video Saliency Estimationcited by 9
  34. 2022Depth-Cooperated Trimodal Network for Video Salient Object Detectioncited by 9
  35. 2020DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detectioncited by 8
  36. 2017Learning RGB-D Salient Object Detection using background enclosure, depth contrast, and top-down featurescited by 7
  37. 2021Confidence-guided Adaptive Gate and Dual Differential Enhancement for Video Salient Object Detectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspectivecited by 6
  2. 2025LEAF-Mamba: Local Emphatic and Adaptive Fusion State Space Model for RGB-D Salient Object Detectioncited by 2
  3. 2026STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detectioncited by 2
  4. 2025Unleashing the Power of Motion and Depth: A Selective Fusion Strategy for RGB-D Video Salient Object Detectioncited by 0
  5. 2025Mamba-based Spatio-Frequency Motion Perception for Video Camouflaged Object Detectioncited by 0
  6. 2026DGSSM: Diffusion guided state-space models for multimodal salient object detectioncited by 0
  7. 2026M4-SAM: Multi-Modal Mixture-of-Experts with Memory-Augmented SAM for RGB-D Video Salient Object Detectioncited by 0
  8. 2026RDVSv2: A Large-scale Benchmark for RGB-D Video Salient Object Detectioncited by 0