arXiv:2610.10047v1 Announce Type: new Abstract: Product-centric advertisement video generation aims to create promotional videos that preserve fine-grained product identity while presenting selling p...
arXiv:2610.33377v1 Announce Type: cross Abstract: Advertisers routinely create multiple duration variants of ads to meet marketing budgets and viewer preferences, a labor-intensive and costly process...
TLive-Omni is an omni‑modal understanding model designed for e‑commerce live streaming, integrating image, video, audio, and text inputs into a unified representation. It introduces Per‑vGrid for timestamped token organization, a three‑stage supervised training pipeline, and a Faithful‑RFT reinforcement fine‑tuning stage to enhance answer faithfulness and expression quality. The model is supported by a scenario‑oriented capability taxonomy and a compact data production engine that generates training signals for tasks such as speech recognition, product visual grounding, and omni‑modal QA, achieving strong performance on live‑commerce benchmarks and good generalization to general tasks.
The paper introduces GPUB, a large-scale benchmark for grounded product understanding in e‑commerce livestream videos, featuring 3,000 livestreams, 31K fashion products, and multi‑moment temporal annotations. It defines three evaluation tasks, with the main task (GPrU) requiring simultaneous product identification and moment localization. Existing multimodal models perform poorly on GPrU, prompting the authors to develop UniPro, which improves performance by learning product‑aligned, temporally structured representations.
The paper introduces AdsCVR, a benchmark for e‑commerce cross‑video reasoning with 2,483 videos and 6,110 QA pairs across six reasoning dimensions. It proposes AdSeek, an agentic framework that actively selects visual and audio tools during multi‑turn exploration and uses an offline trajectory rectification mechanism to improve reinforcement learning. AdSeek achieves 74.30% accuracy on AdsCVR, outperforming its backbone by 27.90 percentage points and generalizes to the open‑domain CrossVid benchmark.
arXiv:2606. 19627v1 Announce Type: cross Abstract: The digital commerce landscape is shifting from static, search-driven catalogs to dynamic, immersive video feeds.
arXiv:2607. 11798v1 Announce Type: cross Abstract: Long-form audio description (AD) requires more than describing visible actions: it must preserve characters, events, relationships, and story context across scenes so that blind and low-vision (BLV) audiences can follow a film.
arXiv:2606. 03635v1 Announce Type: cross Abstract: Understanding short online videos involves more than identifying visible objects and actions; video makers often include an underlying message or purpose in the clip.
arXiv:2607. 29002v1 Announce Type: new Abstract: Online shoppers increasingly turn to AI shopping assistants, using images and multi-turn dialogue to express and refine product needs that are difficult to articulate in text alone.
arXiv:2606. 19103v1 Announce Type: cross Abstract: Recent advances in instruction-based image editing have enabled models to perform complex visual edits from natural language instructions.
The paper introduces Cue2Narrate, a two‑stage pipeline that jointly predicts what visual events to narrate and when to insert the narration in long, untrimmed movie clips. It uses a dual‑head audio‑visual localizer to identify visual cue and narration windows, followed by a LoRA‑adapted vision‑language model that generates concise audio descriptions, trained with a Description Ranking Loss. The authors also present the LongLSMDC benchmark, comprising up to 8‑minute clips, and show that Cue2Narrate outperforms video‑only and audio‑only baselines by 5–12 points in average mAP and improves AD generation over fine‑tuned base VLMs.
arXiv:2606. 01285v1 Announce Type: cross Abstract: Text-to-video generation has advanced rapidly in visual quality, but remains under-evaluated for factuality and practical usefulness.