VCG: A Multimodal Retrieval Framework for E-Commerce Video Feeds under Extreme Cold-Start Conditions

• URL: http://arxiv.org/abs/2606.19627v1
• Date: Wed, 17 Jun 2026 22:08:31 GMT
• Title: VCG: A Multimodal Retrieval Framework for E-Commerce Video Feeds under Extreme Cold-Start Conditions
• Abstract summary: New short-form videos lack the dense interaction history required for collaborative filtering.<n> immersive feeds introduce strong position and duration biases that distort standard engagement signals.<n>We demonstrate a scalable multimodal retrieval engine designed to solve these challenges in a large-scale e-commerce environment.
• Score: 2.5997680822076688
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The digital commerce landscape is shifting from static, search-driven catalogs to dynamic, immersive video feeds. This transition introduces an ``extreme cold-start'' problem: unlike traditional items, new short-form videos lack the dense interaction history required for collaborative filtering. Furthermore, immersive feeds introduce strong position and duration biases that distort standard engagement signals. In this paper, we demonstrate the Video Candidate Generation (VCG) system, a scalable multimodal retrieval engine designed to solve these challenges in a large-scale e-commerce environment. By leveraging a domain-adapted vision-language model (based on CLIP), we map users and videos into a shared semantic space, enabling zero-shot retrieval based on visual content rather than behavioral history. We detail the system's architecture and present a rigorous evaluation comparing generative (LLM) vs. discriminative (CLIP) embeddings. Our results show that while generative models excel at attribute prediction, they suffer from embedding space collapse in retrieval tasks. Online A/B testing demonstrates that VCG effectively mitigates engagement biases, yielding a 50\% uplift in deep video completion. To showcase the system's capabilities, we present an interactive demonstration featuring three bi-directional retrieval scenarios: Product-to-Video, Video-to-Product, and Zero-Shot Semantic Search.

Related papers

• DiVA: Enabling Interactive Digital Life Simulation via Video Models [107.640138694388]
  DiVA is an interactive digital life simulator pioneering a new paradigm for long-term, open-ended interactive experiences.<n>It maintains long-term visual quality and realism, validating its effectiveness as a sustainable, interactive simulation.
  arXiv  Detail & Related papers  (2026-09-12T09:33:15Z)
• Act2See: Emergent Active Visual Perception for Video Reasoning [70.52373240573856]
  Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning.<n>We introduce Act-to-See (Act2See), a novel framework that enables active visual perception.
  arXiv  Detail & Related papers  (2026-05-03T00:52:51Z)
• Video-BrowseComp: Benchmarking Agentic Video Research on Open Web [64.53060049124961]
  Video-BrowseComp is a benchmark comprising 210 questions tailored for open-web agentic video reasoning.<n>It enforces a mandatory dependency on temporal visual evidence, ensuring answers cannot be derived solely through text search.<n>As the first open-web video research benchmark, Video-BrowseComp advances the field beyond passive perception toward proactive video reasoning.
  arXiv  Detail & Related papers  (2025-12-28T19:08:27Z)
• MADTempo: An Interactive System for Multi-Event Temporal Video Retrieval with Query Augmentation [2.819801450768979]
  We introduce MADTempo, a video retrieval framework developed by our team, AIO_Trinh.<n>Our temporal search mechanism captures event-level continuity by aggregating similarity scores across sequential video segments.<n>A Google Image Search-based fallback module expands query representations with external web imagery.
  arXiv  Detail & Related papers  (2025-12-15T02:25:46Z)
• LMVC: An End-to-End Learned Multiview Video Coding Framework [13.78537496324905]
  Multiview video is a key data source for volumetric video, enabling immersive 3D scene reconstruction.<n>Deep learning-based end-to-end video coding has achieved great success, yet most focus on single-view or stereo videos.<n>This paper proposes an end-to-end learned multiview video coding framework that ensures random access and backward compatibility.
  arXiv  Detail & Related papers  (2025-09-04T06:15:41Z)
• Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning [56.873534081386]
  A new topic HIREST is presented, including video retrieval, moment retrieval, moment segmentation, and step-captioning.<n>We propose a query-centric audio-visual cognition network to construct a reliable multi-modal representation for three tasks.<n>This can cognize user-preferred content and thus attain a query-centric audio-visual representation for three tasks.
  arXiv  Detail & Related papers  (2024-12-18T06:43:06Z)
• Live Video Captioning [0.6291443816903801]
  We introduce a groundbreaking paradigm: Live Video Captioning (LVC), where captions must be generated for video streams in an online manner.<n>We formally define the novel problem of LVC and propose innovative evaluation metrics specifically designed for this online scenario.<n>We present a new model that combines deformable transformers with temporal filtering, enabling effective captioning over video streams.
  arXiv  Detail & Related papers  (2024-06-20T11:25:16Z)
• DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries [60.09774333024783]
  We introduce Dynamic Anchor Queries (DAQ) to shorten the transition gap between the anchor and target queries. We also introduce a query-level object Emergence and Disappearance Simulation (EDS) strategy, which unleashes DAQ's potential without any additional cost. Experiments demonstrate that DVIS-DAQ achieves a new state-of-the-art (SOTA) performance on five mainstream video segmentation benchmarks.
  arXiv  Detail & Related papers  (2024-03-29T17:58:50Z)
• VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding [63.075626670943116]
  We introduce a cutting-edge framework, VaQuitA, designed to refine the synergy between video and textual information. At the data level, instead of sampling frames uniformly, we implement a sampling method guided by CLIP-score rankings. At the feature level, we integrate a trainable Video Perceiver alongside a Visual-Query Transformer.
  arXiv  Detail & Related papers  (2023-12-04T19:48:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.