Papers › Revisiting Video Saliency: A Large-scale Benchmark and a New Model
Revisiting Video Saliency: A Large-scale Benchmark and a New Model
Wenguan Wang, Jianbing Shen, Fang Guo, Ming-Ming Cheng, Ali Borji
In this work, we contribute to video saliency research in two ways. First, we introduce a new benchmark for predicting human eye movements during dynamic scene free-viewing, which is long-time urged in this field. Our dataset, named DHF1K (Dynamic Human Fixation), consists of 1K high-quality, elaborately selected video sequences spanning a large range of scenes, motions, object types and background complexity. Existing video saliency datasets lack variety and generality of common dynamic scenes and fall short in covering challenging situations in unconstrained environments. In contrast, DHF1K makes a significant leap in terms of scalability, diversity and difficulty, and is expected to boost video saliency modeling. Second, we propose a novel video saliency model that augments the CNN-LSTM network architecture with an attention mechanism to enable fast, end-to-end saliency learning. The attention mechanism explicitly encodes static saliency information, thus allowing LSTM to focus on learning more flexible temporal saliency representation across successive frames. Such a design fully leverages existing large-scale static fixation datasets, avoids overfitting, and significantly improves training efficiency and testing performance. We thoroughly examine the performance of our model, with respect to state-of-the-art saliency models, on three large-scale datasets (i.e., DHF1K, Hollywood2, UCF sports). Experimental results over more than 1.2K testing videos containing 400K frames demonstrate that our model outperforms other competitors.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Saliency Detection | MSU Video Saliency Prediction | ACLNet | AUC-J | 0.839 | #8 of 14 | Archive leaderboard | report |
| Video Saliency Detection | MSU Video Saliency Prediction | ACLNet | CC | 0.651 | #8 of 14 | Archive leaderboard | report |
| Video Saliency Detection | MSU Video Saliency Prediction | ACLNet | FPS | 4.18 | #8 of 14 | Archive leaderboard | report |
| Video Saliency Detection | MSU Video Saliency Prediction | ACLNet | KLDiv | 0.593 | #8 of 14 | Archive leaderboard | report |
| Video Saliency Detection | MSU Video Saliency Prediction | ACLNet | NSS | 1.71 | #8 of 14 | Archive leaderboard | report |
| Video Saliency Detection | MSU Video Saliency Prediction | ACLNet | SIM | 0.586 | #8 of 14 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections