mlsanityData to 7 Oct 2026

EviDETR: Preserving Query-Relevant Temporal Evidence for Moment Retrieval and Highlight Detection

arXiv 2609.30724 ↗First posted 25 Sep 2026cs.CVcited by 0

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

Joint video moment retrieval and highlight detection requires identifying query-relevant temporal segments while estimating clip-level saliency, yet DETR-style pipelines do not explicitly preserve query-relevant evidence throughout encoding, decoding, and cross-task prediction. We propose EviDETR, an evidence-preserving framework with three components. Semantic-aware Feature Reweighting (SFR) enhances query-relevant clip representations through saliency estimation and cross-modal interaction. A Temporal Top-2 Mixture-of-Experts (TTop2MoE) decoder performs query-adaptive refinement via sparse expert routing. MR-to-HD (MR2HD) fusion transfers span-level retrieval evidence to clip-level highlight prediction through confidence-weighted multi-scale aggregation. Using CLIP+SlowFast features, EviDETR achieves 69.29 [email protected], 54.77 [email protected], and 48.41 Avg. mAP for moment retrieval on QVHighlights, together with 41.83 HD-mAP and 68.33 HIT@1. Strong results on TACoS and Charades-STA further demonstrate cross-dataset transferability.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 13 of its 18 references that are in the map. First posted on arXiv 25 Sep 2026.

Builds on

13 of 18 references.

References · 13

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2017Mask R-CNNcited by 7,259
  4. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  5. 2018SlowFast Networks for Video Recognitioncited by 1,862
  6. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  7. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  8. 2017TALL: Temporal Activity Localization via Language Querycited by 581
  9. 2023Query-Dependent Video Representation for Moment Retrieval and Highlight Detectioncited by 166
  10. 2024TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detectioncited by 59
  11. 2023BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videoscited by 29
  12. 2025LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detectioncited by 8
1 more
  1. 2025The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025See, Rank, and Filter: Important Word-Aware Clip Filtering via Scene Understanding for Moment Retrieval and Highlight Detection
  2. 2026TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval
  3. 2025SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM
  4. 2024VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval
  5. 2026TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
  6. 2025MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
  7. 2025MADTempo: An Interactive System for Multi-Event Temporal Video Retrieval with Query Augmentation
  8. 2026Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning