Browse State-of-the-Art › Video Saliency Detection
Video Saliency Detection
21 papers with code · 5 benchmarks · 3 datasets archive 2025-07-28
Video Saliency Detection is the process of detecting or predicting the most visually important or attention-grabbing regions in video sequence. This regions are where humans most likely focus their attention when watching the video.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| MSU Video Saliency Prediction (14 rows) | ViNet (dave) | ViNet: Pushing the limits of Visual Modality for Audio-Visual... | code | — | Compare |
| DHF1K (3 rows) | ViNet | ViNet: Pushing the limits of Visual Modality for Audio-Visual... | code | — | Compare |
| DIEM (1 row) | AViNet | ViNet: Pushing the limits of Visual Modality for Audio-Visual... | code | — | Compare |
| Hollywood2 (1 row) | ViNet | ViNet: Pushing the limits of Visual Modality for Audio-Visual... | code | — | Compare |
| UCFSports (1 row) | ViNet | ViNet: Pushing the limits of Visual Modality for Audio-Visual... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 36 · with a code link: 21 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 36 tagged: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 36 of 36, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
18 Feb 2019 4 repositories listed Syntology official: harvested, nothing ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples)To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted and augmented with contextual information.
-
11 Mar 2020 2 repositories listed Syntology official (archive's flag): 6 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 1 pointer-only (licence)We evaluate our method on the video saliency datasets DHF1K, Hollywood-2 and UCF-Sports, and the image saliency datasets SALICON and MIT300.
-
3 Jul 2019 2 repositories listedThis paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain.
-
23 Sep 2024 1 repository listedThe goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences.
-
18 Jun 2024 1 repository listedHowever, the existing salient object detection (SOD) works only focus on either static RGB-D images or RGB videos, ignoring the collaborating of RGB-D and video information.
-
5 Dec 2023 1 repository listedIn this work, we present an integrated system for spatiotemporal summarization of 360-degrees videos.
-
19 Sep 2022 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples)360° video saliency detection is one of the challenging benchmarks for 360° video understanding since non-negligible distortion and discontinuity occur in the projection of any format of 360° videos, and capture-worthy…
-
20 Jun 2022 1 repository listedVideo saliency detection (VSD) aims at fast locating the most attractive objects/things/patterns in a given video clip.
-
9 Jun 2022 1 repository listedWe show that gaze direction and affective representations contribute a prediction to ground-truth correspondence improvement of at least 5% compared to dynamic saliency models without social cues.
-
27 Dec 2021 1 repository listedMoreover, we distill knowledge from these regions to obtain complete new spatial-temporal-audio (STA) fixation prediction (FP) networks, enabling broad applications in cases where video tags are not available.
-
19 Jun 2021 1 repository listedThanks to the rapid advances in the deep learning techniques and the wide availability of large-scale training sets, the performances of video saliency detection models have been improving steadily and significantly.
-
6 Apr 2021 1 repository listedSignificant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain.
-
11 Dec 2020 1 repository listedWe also explore a variation of ViNet architecture by augmenting audio features into the decoder.
-
2 Oct 2020 1 repository listedWhen the base hierarchical model is empowered with domain-specific modules, performance improves, outperforming state-of-the-art models on three out of five metrics on the DHF1K benchmark and reaching the second-best…
-
7 Aug 2020 1 repository listedIn this way, even though the overall video saliency quality is heavily dependent on its spatial branch, however, the performance of the temporal branch still matter.
-
2 Aug 2020 1 repository listedWith the rapid development of deep learning techniques, image saliency deep models trained solely by spatial information have occasionally achieved detection performance for video data comparable to that of the models…
-
2 Jan 2020 1 repository listedDue to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP).
-
15 Aug 2019 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)It consists of two building blocks: first, the encoder network extracts low-resolution spatiotemporal features from an input clip of several consecutive frames, and then the following prediction network decodes the…
-
7 Apr 2019 1 repository listedIn this work, we proposed an end-to-end dilated inception network (DINet) for visual saliency prediction.
-
1 Sep 2018 1 repository listedHence, 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.
-
23 Jan 2018 1 repository listedExisting video saliency datasets lack variety and generality of common dynamic scenes and fall short in covering challenging situations in unconstrained environments.
-
Saliency Detection in Educational Videos: Analyzing the Performance of Current Models, Identifying Limitations and Advancement Directions8 Aug 2024 0 repositories listedIdentifying the regions of a learning resource that a learner pays attention to is crucial for assessing the material's impact and improving its design and related support systems.
-
Temporal-Spatial Feature Pyramid for Video Saliency Detection10 May 2021 0 repositories listedMulti-level features are important for saliency detection.
-
Learning to Explore Intrinsic Saliency for Stereoscopic Video1 Jun 2019 0 repositories listedThe human visual system excels at biasing the stereoscopic visual signals by the attention mechanisms.
-
Unsupervised uncertainty estimation using spatiotemporal cues in video saliency detection6 Jan 2019 0 repositories listedIn this paper, we address the problem of quantifying reliability of computational saliency for videos, which can be used to improve saliency-based video processing and enable more reliable performance and risk…
-
Global and Local Sensitivity Guided Key Salient Object Re-augmentation for Video Saliency Detection19 Nov 2018 0 repositories listedThe existing still-static deep learning based saliency researches do not consider the weighting and highlighting of extracted features from different layers, all features contribute equally to the final saliency…
-
Salient Object Detection in Video using Deep Non-Local Neural Networks16 Oct 2018 0 repositories listedDetection of salient objects in image and video is of great importance in many computer vision applications.
-
SG-FCN: A Motion and Memory-Based Deep Learning Model for Video Saliency Detection21 Sep 2018 0 repositories listedData-driven saliency detection has attracted strong interest as a result of applying convolutional neural networks to the detection of eye fixations.
-
Saliency Detection in 360° Videos1 Sep 2018 0 repositories listedThis paper presents a novel spherical convolutional neural network based scheme for saliency detection for 360° videos.
-
Video Saliency Detection by 3D Convolutional Neural Networks12 Jul 2018 0 repositories listedDifferent from salient object detection methods for still images, a key challenging for video saliency detection is how to extract and combine spatial and temporal features.
-
Review of Visual Saliency Detection with Comprehensive Information9 Mar 2018 0 repositories listed
-
Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection25 Jul 2017 0 repositories listed
-
6 May 2016 0 repositories listed
-
Encoding Based Saliency Detection for Videos and Images1 Jun 2015 0 repositories listed
-
4 Dec 2006 0 repositories listed
-
1 Nov 1998 0 repositories listed
Syntology lines on 4 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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