paper-with-me

홈 › Papers

OFAR: A Multimodal Evidence Retrieval Framework for Illegal Live-streaming Identification

2023-04-25 · Lin Dengtian, Ma Yang, Li Yuhong, Song Xuemeng, Wu Jianlong, Nie Liqiang

Illegal live-streaming identification, which aims to help live-streaming platforms immediately recognize the illegal behaviors in the live-streaming, such as selling precious and endangered animals, plays a crucial role in purifying the network environment. Traditionally, the live-streaming platform needs to employ some professionals to manually identify the potential illegal live-streaming. Specifically, the professional needs to search for related evidence from a large-scale knowledge database for evaluating whether a given live-streaming clip contains illegal behavior, which is time-consuming and laborious. To address this issue, in this work, we propose a multimodal evidence retrieval system, named OFAR, to facilitate the illegal live-streaming identification. OFAR consists of three modules: Query Encoder, Document Encoder, and MaxSim-based Contrastive Late Intersection. Both query encoder and document encoder are implemented with the advanced OFA encoder, which is pretrained on a large-scale multimodal dataset. In the last module, we introduce contrastive learning on the basis of the MaxiSim-based late intersection, to enhance the model's ability of query-document matching. The proposed framework achieves significant improvement on our industrial dataset TaoLive, demonstrating the advances of our scheme.

📄 PDF Abstract BibTeX arXiv:2304.12608

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningRetrieval

Methods 이 논문이 사용한 방법론

OFA In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…
Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

COFAR: Commonsense and Factual Reasoning in Image Search

2022-10-16 · Prajwal Gatti, Abhirama Subramanyam Penamakuri, Revant Teotia, Anand Mishra 외

One characteristic that makes humans superior to modern artificially intelligent models is the ability to interpret images beyond what is visually apparent. Consider the following two natural language search queries - (i…

Image RetrievalRetrievalWorld Knowledge

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

2026-02-05 · Dongyang Chen, Chaoyang Wang, Dezhao Su, Xi Xiao 외 arxiv

Multimodal Large Language Models (MLLMs) have recently been applied to universal multimodal retrieval, where Chain-of-Thought (CoT) reasoning improves candidate reranking. However, existing approaches remain largely lang…

Reinforcement Learning

MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering

2026-02-01 · Hui Wu, Haoquan Zhai, Yuchen Li, Hengyi Cai 외 arxiv

Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmented generation (RAG) has shown strong perf…

Question Answering

Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering

2023-10-15 · Shuwen Yang, Anran Wu, Xingjiao Wu, Luwei Xiao 외

Pre-trained multimodal models have achieved significant success in retrieval-based question answering. However, current multimodal retrieval question-answering models face two main challenges. Firstly, utilizing compress…

Contrastive LearningLogical SequenceQuestion AnsweringRetrieval

BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation

2026-01-12 · Xuan Li, Yining Wang, Haocai Luo, Shengping Liu 외 arxiv

Retrieval-Augmented Generation (RAG) has become a pivotal paradigm for Large Language Models (LLMs), yet current approaches struggle with visually rich documents by treating text and images as isolated retrieval targets.…

Bayesian Inference