AI Paper Atlas

Research map / Video / Video segmentation and tracking

SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object Detection

Jia Lin, Xiaofei Zhou, Jiyuan Liu, Runmin Cong, Guodao Zhang, Zhi Liu, Jiyong Zhang

AAAI 2026 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use parallel depth-guided adapters instead of sequential adapters (ablation)SAM-DAQ PAMIE · RDVStraining memory (G): 91.9 -> 21.0 GB; E-measure 0.860 -> 0.913Improved
use parallel adapters instead of LoRA (ablation)SAM-DAQ PAMIE · RDVStraining memory (G): 95.0 -> 21.0 GB; E 0.889 -> 0.913Improved
add linear depth projector (ablation)SAM-DAQ · RDVSE-measure: 0.899 -> 0.913Improved
add depth modality (multi-modal fusion) (ablation)SAM-DAQ · RDVSE-measure: 0.876 -> 0.913Improved
use sparse-only learnable embeddings instead of dense or both (ablation)QTM · RDVSE-measure: 0.875 (dense) / 0.862 (both) -> 0.913Improved
add iterative video-level query update (ablation)QTM · RDVSE-measure: 0.883 -> 0.913Improved
replace SAM2 memory bank with QTM (ablation)SAM-DAQ · RDVSE-measure: 0.853 -> 0.913Improved
addition update instead of multiply update (ablation)QTM · RDVSE-measure: 0.895 -> 0.913Improved
supervise only highest-level embeddings instead of all three levels (ablation)SAM-DAQ intermediate supervision · RDVSE-measure: 0.845 -> 0.913Improved
increase query hidden dimension beyond 64 (ablation)QTM · RDVSE-measure: 0.913 (64) -> 0.874 (128), 0.880 (256)Hurt
increase video-level queries to 10 from 8 (ablation)QTM · RDVSE/S/F-measureHurt
SAM-DAQ vs KAN-SAM (best SAM-based baseline)SAM-DAQ · RDVS, ViDSOD-100, DViSalE-measure: 0.888 -> 0.913 (RDVS)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy