Papers › Multi-Attention Network for Compressed Video Referring Object Segmentation

Multi-Attention Network for Compressed Video Referring Object Segmentation

26 Jul 2022arXiv:2207.12622archive 2025-07-28

Weidong Chen, Dexiang Hong, Yuankai Qi, Zhenjun Han, Shuhui Wang, Laiyun Qing, Qingming Huang, Guorong Li

Referring video object segmentation aims to segment the object referred by a given language expression. Existing works typically require compressed video bitstream to be decoded to RGB frames before being segmented, which increases computation and storage requirements and ultimately slows the inference down. This may hamper its application in real-world computing resource limited scenarios, such as autonomous cars and drones. To alleviate this problem, in this paper, we explore the referring object segmentation task on compressed videos, namely on the original video data flow. Besides the inherent difficulty of the video referring object segmentation task itself, obtaining discriminative representation from compressed video is also rather challenging. To address this problem, we propose a multi-attention network which consists of dual-path dual-attention module and a query-based cross-modal Transformer module. Specifically, the dual-path dual-attention module is designed to extract effective representation from compressed data in three modalities, i.e., I-frame, Motion Vector and Residual. The query-based cross-modal Transformer firstly models the correlation between linguistic and visual modalities, and then the fused multi-modality features are used to guide object queries to generate a content-aware dynamic kernel and to predict final segmentation masks. Different from previous works, we propose to learn just one kernel, which thus removes the complicated post mask-matching procedure of existing methods. Extensive promising experimental results on three challenging datasets show the effectiveness of our method compared against several state-of-the-art methods which are proposed for processing RGB data. Source code is available at: https://github.com/DexiangHong/MANet.

PaperPDFCode

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

Code

dexianghong/manet officialmentioned in paperpytorch report

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

ObjectReferring Expression SegmentationReferring Video Object SegmentationSegmentationSemantic SegmentationVideo Object SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation A2D Sentences MANET AP 0.471 #5 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences MANET IoU mean 0.632 #5 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences MANET IoU overall 0.726 #5 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences MANET Precision@0.5 0.734 #5 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences MANET Precision@0.6 0.682 #5 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences MANET Precision@0.7 0.579 #5 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences MANET Precision@0.8 0.389 #5 of 27 Archive leaderboard report
Referring Expression Segmentation A2D Sentences MANET Precision@0.9 0.132 #5 of 27 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) MANET F 56.51 #26 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) MANET J 54.75 #26 of 33 Archive leaderboard report
Referring Expression Segmentation Refer-YouTube-VOS (2021 public validation) MANET J&F 55.63 #26 of 33 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Attention NetworkMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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