</> Code with Papers by Syntology

Papers › Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation

Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation

14 May 2021CVPR 2021 1arXiv:2105.06818archive 2025-07-28

Tianrui Hui, Shaofei Huang, Si Liu, Zihan Ding, Guanbin Li, Wenguan Wang, Jizhong Han, Fei Wang

Language-queried video actor segmentation aims to predict the pixel-level mask of the actor which performs the actions described by a natural language query in the target frames. Existing methods adopt 3D CNNs over the video clip as a general encoder to extract a mixed spatio-temporal feature for the target frame. Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation. Therefore, we propose a collaborative spatial-temporal encoder-decoder framework which contains a 3D temporal encoder over the video clip to recognize the queried actions, and a 2D spatial encoder over the target frame to accurately segment the queried actors. In the decoder, a Language-Guided Feature Selection (LGFS) module is proposed to flexibly integrate spatial and temporal features from the two encoders. We also propose a Cross-Modal Adaptive Modulation (CMAM) module to dynamically recombine spatial- and temporal-relevant linguistic features for multimodal feature interaction in each stage of the two encoders. Our method achieves new state-of-the-art performance on two popular benchmarks with less computational overhead than previous approaches.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderReferring Expression Segmentationfeature selection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation A2D Sentences Hui et al. AP 0.399 #12 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences Hui et al. IoU mean 0.561 #12 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences Hui et al. IoU overall 0.662 #12 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences Hui et al. Precision@0.5 0.654 #12 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences Hui et al. Precision@0.6 0.589 #12 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences Hui et al. Precision@0.7 0.497 #12 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences Hui et al. Precision@0.8 0.333 #12 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences Hui et al. Precision@0.9 0.091 #12 of 27 Archive leaderboard report
Referring Expression Segmentation J-HMDB Hui et al. AP 0.335 #8 of 21 Archive leaderboard report
Referring Expression Segmentation J-HMDB Hui et al. IoU mean 0.604 #8 of 21 Archive leaderboard report
Referring Expression Segmentation J-HMDB Hui et al. IoU overall 0.598 #8 of 21 Archive leaderboard report
Referring Expression Segmentation J-HMDB Hui et al. Precision@0.5 0.783 #8 of 21 Archive leaderboard report
Referring Expression Segmentation J-HMDB Hui et al. Precision@0.6 0.639 #8 of 21 Archive leaderboard report
Referring Expression Segmentation J-HMDB Hui et al. Precision@0.7 0.378 #8 of 21 Archive leaderboard report
Referring Expression Segmentation J-HMDB Hui et al. Precision@0.8 0.076 #8 of 21 Archive leaderboard report
Referring Expression Segmentation J-HMDB Hui et al. Precision@0.9 0.000 #8 of 21 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

Feature Selection

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