Renmin University Of China At TRECVID 2022: Improving Video Search By Feature Fusion And Negation Understanding
2022 · Xirong Li, Aozhu Chen, Ziyue Wang, et al.
Abstract
We summarize our TRECVID 2022 Ad-hoc Video Search (AVS) experiments. Our solution is built with two new techniques, namely Lightweight Attentional Feature Fusion (LAFF) for combining diverse visual / textual features and Bidirectional Negation Learning (BNL) for addressing queries that contain negation cues. In particular, LAFF performs feature fusion at both early and late stages and at both text and video ends to exploit diverse (off-the-shelf) features. Compared to multi-head self attention, LAFF is much more compact yet more effective. Its attentional weights can also be used for selecting fewer features, with the retrieval performance mostly preserved. BNL trains a negation-aware video retrieval model by minimizing a bidirectionally constrained loss per triplet, where a triplet consists of a given training video, its original description and a partially negated description. For video feature extraction, we use pre-trained CLIP, BLIP, BEiT, ResNeXt-101 and irCSN. As for text featur
Authors
(none)
Tags
Stats
Related papers
- Lightweight Attentional Feature Fusion: A New Baseline For Text-to-video Retrieval (2021)12.02
- Learning Video Retrieval Models With Relevance-aware Online Mining (2022)6.07
- Dual-modal Attention-enhanced Text-video Retrieval With Triplet Partial Margin Contrastive Learning (2023)8.82
- Revitalize Region Feature For Democratizing Video-language Pre-training Of Retrieval (2022)2.72
- X-aligner: Composed Visual Retrieval Without The Bells And Whistles (2026)0.00
- Discovla: Discrepancy Reduction In Vision, Language, And Alignment For Parameter-efficient Video-text Retrieval (2025)6.30
- TRECVID 2019: An Evaluation Campaign To Benchmark Video Activity Detection, Video Captioning And Matching, And Video Search & Retrieval (2020)0.00
- MMMORRF: Multimodal Multilingual Modularized Reciprocal Rank Fusion (2025)2.26