Papers › DeepVS: A Deep Learning Based Video Saliency Prediction Approach

DeepVS: A Deep Learning Based Video Saliency Prediction Approach

1 Sep 2018ECCV 2018 9archive 2025-07-28

Lai Jiang, Mai Xu, Tie Liu, Minglang Qiao, Zulin Wang

In this paper, we propose a novel deep learning based video saliency prediction method, named DeepVS. Specifically, we establish a large-scale eye-tracking database of videos (LEDOV), which includes 32 subjects' fixations on 538 videos. We find from LEDOV that human attention is more likely to be attracted by objects, particularly the moving objects or the moving parts of objects. Hence, an object-to-motion convolutional neural network (OM-CNN) is developed to predict the intra-frame saliency for DeepVS, which is composed of the objectness and motion subnets. In OM-CNN, cross-net mask and hierarchical feature normalization are proposed to combine the spatial features of the objectness subnet and the temporal features of the motion subnet. We further find from our database that there exists a temporal correlation of human attention with a smooth saliency transition across video frames. We thus propose saliency-structured convolutional long short-term memory (SS-ConvLSTM) network, using the extracted features from OM-CNN as the input. Consequently, the inter-frame saliency maps of a video can be generated, which consider both structured output with center-bias and cross-frame transitions of human attention maps. Finally, the experimental results show that DeepVS advances the state-of-the-art in video saliency prediction.

PaperPDFCode

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

Deep LearningPredictionSaliency PredictionVideo Saliency DetectionVideo Saliency Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Saliency Detection MSU Video Saliency Prediction DeepVS AUC-J 0.804 #12 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DeepVS CC 0.586 #12 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DeepVS FPS 3.29 #12 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DeepVS KLDiv 0.707 #12 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DeepVS NSS 1.44 #12 of 14 Archive leaderboard report
Video Saliency Detection MSU Video Saliency Prediction DeepVS SIM 0.548 #12 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.

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