Multi-modal Transformer for Video Retrieval

2020/07/21 by Valentin Gabeur, Gabeur, Valentin, Chen Sun +5 · 32 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Video Analysis and Summarization #cs.CV

paper · pdf · doi:10.48550/arxiv.2007.10639

ECCV 2020 (spotlight paper)

arxiv created 2020/07/21 · openalex publication_date 2020/07/21 · arxiv updated 2020/07/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The task of retrieving video content relevant to natural language queries plays a critical role in effectively handling internet-scale datasets. Most of the existing methods for this caption-to-video retrieval problem do not fully exploit cross-modal cues present in video. Furthermore, they aggregate per-frame visual features with limited or no temporal information. In this paper, we present a multi-modal transformer to jointly encode the different modalities in video, which allows each of them to attend to the others. The transformer architecture is also leveraged to encode and model the temporal information. On the natural language side, we investigate the best practices to jointly optimize the language embedding together with the multi-modal transformer. This novel framework allows us to establish state-of-the-art results for video retrieval on three datasets. More details are available at http://thoth.inrialpes.fr/research/MMT.

Citations

• Efficient Estimation of Word Representations in Vector Space
• Two-Stream Convolutional Networks for Action Recognition in Videos
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Use What You Have: Video Retrieval Using Representations From Collaborative Experts
• HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

Cited by

• DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning
• OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction
• Unified Interactive Multimodal Moment Retrieval via Cascaded Embedding-Reranking and Temporal-Aware Score Fusion
• VDC-Agent: When Video Detailed Captioners Evolve Themselves via Agentic Self-Reflection
• Reasoning Text-to-Video Retrieval via Digital Twin Video Representations and Large Language Models
• Mitigating Semantic Collapse in Partially Relevant Video Retrieval
• Multimedia-Aware Question Answering: A Review of Retrieval and Cross-Modal Reasoning Architectures
• MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval
• Dual Learning with Dynamic Knowledge Distillation and Soft Alignment for Partially Relevant Video Retrieval
• Queries Are Not Alone: Clustering Text Embeddings for Video Search
• ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
• Advancing Reference-free Evaluation of Video Captions with Factual Analysis
• Video Understanding by Design: How Datasets Shape Architectures and Insights
• Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes
• Harnessing Object Grounding for Time-Sensitive Video Understanding
• Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
• ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval
• A CLIP-based Uncertainty Modal Modeling (UMM) Framework for Pedestrian Re-Identification in Autonomous Driving
• Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search
• GAIS: Frame-Level Gated Audio-Visual Integration with Semantic Variance-Scaled Perturbation for Text-Video Retrieval
• Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval
• Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization
• T2VParser: Adaptive Decomposition Tokens for Partial Alignment in Text to Video Retrieval
• DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
• Smart Routing for Multimodal Video Retrieval: When to Search What
• BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance
• Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review
• Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
• PHA-Net: Prototype-based Hierarchical Alignment Network for Text-Video Retrieval
• Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining
• TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
• TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video Retrieval
• Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis

Related

• Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval
• Leveraging Modality Tags for Enhanced Cross-Modal Video Retrieval
• ConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval
• HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval
• M2HF: Multi-level Multi-modal Hybrid Fusion for Text-Video Retrieval