Research map / Video / Video segmentation and tracking
DeepVS: A Deep Learning Based Video Saliency Prediction Approach
Lai Jiang, Mai Xu, Tie Liu, Minglang Qiao, Zulin Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add auxiliary KL loss on the cross-net mask (ablation) | OM-CNN · LEDOV | KL divergence: decreases KL by 0.24 | Improved |
| combine objectness and motion subnets into OM-CNN (vs objectness subnet alone) (ablation) | OM-CNN · LEDOV | KL divergence: 0.05 reduction in KL divergence | Improved |
| combine objectness and motion subnets into OM-CNN (vs motion subnet alone) (ablation) | OM-CNN · LEDOV | KL divergence: 0.09 KL divergence reduction | Improved |
| add SS-ConvLSTM on top of OM-CNN (ablation) | DeepVS · LEDOV | KL divergence: reduces KL by 0.09 | Improved |
| add center-bias dropout (p=0.75) instead of no CB dropout (ablation) | SS-ConvLSTM · LEDOV validation | KL divergence: reduce KL divergence by 0.03 | Improved |
| lower dropout rates from 0.75 to 0.2 (ablation) | SS-ConvLSTM · LEDOV validation | KL divergence: KL rises by 0.08 | Hurt |
| test with longer clips (24 or 32 frames) than training length 16 (ablation) | SS-ConvLSTM · LEDOV validation | KL divergence: a bit better at 24 or 32 | No clear effect |
| use DeepVS instead of best baseline | DeepVS · LEDOV test | AUC, NSS, CC, KL: 0.01, 0.51, 0.12 and 0.33 improvements | Improved |
| transfer DeepVS trained on LEDOV to DIEM | DeepVS · DIEM | AUC, NSS, CC, KL: 0.05, 0.57, 0.11 and 0.34 improvements | Improved |
| transfer DeepVS trained on LEDOV to SFU | DeepVS · SFU | CC, KL: CC 0.55 vs 0.58; KL 0.67 vs GBVS 0.61 | Mixed |
Later papers that compared with this method
2 later accepted papers report DeepVS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Measuring the Importance of Temporal Features in Video Saliency (ECCV 2020 · better on 2 of 2 shared results)
- Viewport Proposal CNN for 360deg Video Quality Assessment (CVPR 2019 · better on 1 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Revisiting Video Saliency Prediction in the Deep Learning Era (TPAMI 2019 · similarity 0.91)
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (CVPR 2018 · similarity 0.91)
- Saliency Prediction in the Deep Learning Era: Successes and Limitations (TPAMI 2019 · similarity 0.90)
- Predicting Salient Face in Multiple-Face Videos (CVPR 2017 · similarity 0.90)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.89)
- A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
