TAME is a CLIP‑based framework for Text‑Video Retrieval that incorporates temporal modeling through three key innovations: sparse Mixture‑of‑Experts layers with frame‑consistent routing, Frame‑Temporal tokens that aggregate cross‑frame information, and a Cross‑Temporal Interaction and Aggregation module for refining frame‑wise similarities. These components enable the model to capture both local visual patterns and long‑range temporal dependencies, leading to consistent performance gains over CLIP‑based baselines on multiple TVR benchmarks, including a 4.0 R@1 improvement on MSR‑VTT. The code is publicly available on GitHub.
By Uicheol Jung, Juyoung Hong, Hojung Kwon, Yukyung Choi
TAME introduces a Temporal-Aware Mixture-of-Experts framework for Text-Video Retrieval that enhances CLIP-based models by incorporating frame-level structure and temporal relations. It adds sparse Mixture-of-Experts layers with frame-consistent routing, Frame-Temporal tokens for global cross-frame aggregation, and a Cross-Temporal Interaction and Aggregation module to refine sentence-video similarities. Experiments on multiple TVR benchmarks show consistent performance gains, such as a 4.0 R@1 improvement on MSR‑VTT over CLIP4Clip.
arXiv:2608. 11343v1 Announce Type: new Abstract: Multimodal retrieval and classification across different types of media, spanning text, images,video and audio, has traditionally relied on dual-encoder models that align visual and textual representations through contrastive learning.
By Archan Dutta, Vyanktesh Kanungo
arXiv:2604.17422v2 Announce Type: replace
Abstract: Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive cost of processing dens...
By Shaoguang Wang, Weiyu Guo, Ziyang Chen, Xuming Hu, Hui Xiong
The paper introduces ReT-2, a unified retrieval model that handles multimodal queries containing both images and text and searches across multimodal document collections. It employs a recurrent Transformer architecture with LSTM-inspired gating to integrate information across layers and modalities, capturing fine-grained visual and textual details. Evaluations on M2KR and M-BEIR benchmarks show state‑of‑the‑art performance, faster inference, and lower memory usage, and the model also boosts downstream tasks in retrieval‑augmented generation pipelines.
By Davide Caffagni, Sara Sarto, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara
VEDJE is a new video-text retrieval method that compresses video features into a reusable cache while keeping them distinct for each frame. It introduces feature-change prediction as an auxiliary training signal, enabling improved retrieval from the compressed cache without extra cost at query time. Experiments on MSR-VTT, MSVD, DiDeMo, and ActivityNet show that VEDJE boosts R@1 in both retrieval directions, achieving 59.8% text-to-video R@1 on MSR-VTT with a fine-tuned VideoCLIP-XL first stage and maintaining recall when the per-video cache is reduced to 12 KiB.
By Shahaf Wagner, Gabriele Serussi, Dan Ben Ami, Tomer Galanti, Chaim Baskin
SALI (Shot-Aware Late Interaction) is a new method for text-to-video retrieval that addresses the loss of relational information when videos are represented by a single embedding. It extracts the subject and object from a query sentence and matches their text embeddings against each visual shot embedding of a video clip using a greedy max or optimal transport operator, with a film-grammar penalty added during fine‑tuning. Built on CLIP4Clip‑meanP, SALI maintains overall recall on Condensed Movies and ActivityNet while significantly improving R@1 for multi‑shot relation queries, achieving the largest gains among compared methods and modestly improving performance on MSR‑VTT.
By Toya Oyama, Rainer Lienhart, Shin'ichi Satoh
arXiv:2610.08674v1 Announce Type: new
Abstract: Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independentl...
By Yuhao Qin, Junbo Wang, Yuke Li, Yining Zhu
arXiv:2607. 25266v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible.
By Ghazal Kaviani, Ghassan AlRegib
arXiv:2608. 07663v1 Announce Type: cross Abstract: When videos extend from hours to days, directly processing them end-to-end becomes impractical for current Multi-modal Large Language Models (MLLMs).
By Yeeun Choi, Youngbeom Yoo, Joon-Young Lee, Hyolim Kang, Seon Joo Kim
MultiVENT‑Raw is a new multilingual benchmark comprising nearly 120,000 raw videos—continuous footage from cell phones, hand‑held cameras, or CCTV—totaling over 5,300 hours. The dataset includes 130 events and 222 event‑centric queries, along with human‑annotated relevance judgments and extracted key facts for relevant videos. It supports two tasks: retrieving videos relevant to a query event and generating a coherent report summarizing event‑related videos for a target user, with baseline models showing these tasks remain challenging.
By Reno Kriz, David Etter, Alexander Martin, Cameron Carpenter, Debashish Chakraborty, Hannah Recknor, Reihaneh Iranmanesh, Matthew Maciejewski, Kenton Murray, Eugene Yang, Benjamin Van Durme, Aaron Steven White, Andrew Yates, William Walden
arXiv:2606. 00910v1 Announce Type: cross Abstract: Composed Video Retrieval (CoVR) seeks the target video that results from applying a free-form textual modification to a reference video.
By Ali Alavi