Contra: (con)text (tra)nsformer For Cross-modal Video Retrieval

Abstract

In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video segments) can be used to improve the retrieval performance. We propose Context Transformer (ConTra); an encoder architecture that models the interaction between a video clip and its local temporal context in order to enhance its embedded representations. Importantly, we supervise the context transformer using contrastive losses in the cross-modal embedding space. We explore context transformers for video and text modalities. Results consistently demonstrate improved performance on three datasets: YouCook2, EPIC-KITCHENS and a clip-sentence version of ActivityNet Captions. Exhaustive ablation studies and context analysis show the efficacy of the proposed method.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keyfragomeni2022contra

Related papers

• Multi-modal Transformer For Video Retrieval (2020)19.47
• Hit: Hierarchical Transformer With Momentum Contrast For Video-text Retrieval (2021)15.98
• CLIP2TV: Align, Match And Distill For Video-text Retrieval (2021)0.00
• X-CLIP: End-to-end Multi-grained Contrastive Learning For Video-text Retrieval (2022)18.12
• Towards Fast Adaptation Of Pretrained Contrastive Models For Multi-channel Video-language Retrieval (2022)7.50
• Multimodal Contextualized Support For Enhancing Video Retrieval System (2026)0.00
• Crossclr: Cross-modal Contrastive Learning For Multi-modal Video Representations (2021)15.59
• Semantic Role Aware Correlation Transformer For Text To Video Retrieval (2022)6.34