M3TR is a temporal retrieval‑enhanced multi‑modal framework for predicting micro‑video popularity. It introduces a Mamba‑Hawkes Process module to model user feedback as self‑exciting events, capturing long‑range temporal dependencies. A temporal‑aware retrieval engine then identifies historically relevant videos by combining multi‑modal content similarity with popularity trajectory similarity, augmenting the target video’s features for improved prediction accuracy.
arXiv:2606. 27539v1 Announce Type: cross Abstract: Social media popularity prediction aims to forecast the future reach or influence of online content from early-stage observations.
arXiv:2606. 19627v1 Announce Type: cross Abstract: The digital commerce landscape is shifting from static, search-driven catalogs to dynamic, immersive video feeds.
arXiv:2604. 25834v2 Announce Type: replace Abstract: With the rapid development of the Internet, users have increasingly higher expectations for the recommendation accuracy of online content consumption platforms.
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.
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...
arXiv:2607. 06875v1 Announce Type: cross Abstract: Understanding and forecasting audience reactions to video content are crucial for improving content creation, recommendation systems, and media analysis.
arXiv:2609.38839v1 Announce Type: new Abstract: Long-horizon video generation requires models to effectively leverage an increasingly long generation history. As the generated history grows, retainin...
We introduce Predictive State Retrieval (PSR), a task in which a model observes a short video prefix and a temporal question about an object's future state, then retrieves instances from other videos or images that depict that state. Unlike action anticipation, which predicts a label, moment retrieval, which localizes an observed event within a video, or video generation, which synthesizes pixels, PSR combines anticipation with cross-instance retrieval across multiple temporal horizons.
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).
The paper introduces DUMoE, a drift‑aware multimodal user representation framework that models user preferences over time by integrating static profiles, short‑term signals, and long‑term dependencies. It employs a sparse mixture‑of‑experts interest adapter, where each expert captures a distinct latent interest and a gating network selects relevant experts for each user. A three‑stage training strategy decouples backbone learning, expert specialization, and gating optimization, and experiments on real social media data demonstrate that DUMoE outperforms existing methods in user interest and interaction prediction.
TimeBlind is a diagnostic benchmark designed to evaluate fine‑grained spatio‑temporal compositionality in video large language models (LLMs). It categorizes temporal understanding into three levels—atomic event recognition, event property characterization, and reasoning about event interdependencies—and uses a minimal‑pairs paradigm where video pairs share identical static content but differ only in temporal structure. Across 20 state‑of‑the‑art MLLMs tested on 600 curated instances, the best model achieved only 48.2% instance accuracy, far below human performance of 98.2%, highlighting a reliance on static visual shortcuts rather than true temporal reasoning.
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.