DeepAI AI Chat
Log In Sign Up

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

by   Lin Dengtian, et al.
Shandong University
Alibaba Group
Peking University

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.


page 1

page 2

page 3

page 4


CS-lol: a Dataset of Viewer Comment with Scene in E-sports Live-streaming

Billions of live-streaming viewers share their opinions on scenes they a...

Towards Supporting Programming Education at Scale via Live Streaming

Live streaming, which allows streamers to broadcast their work to live v...

You Watch, You Give, and You Engage: A Study of Live Streaming Practices in China

Despite gaining traction in North America, live streaming has not reache...

ContentCTR: Frame-level Live Streaming Click-Through Rate Prediction with Multimodal Transformer

In recent years, live streaming platforms have gained immense popularity...

Hate Raids on Twitch: Understanding Real-Time Human-Bot Coordinated Attacks in Live Streaming Communities

Online harassment and content moderation have been well-documented in on...

LiveChat: A Large-Scale Personalized Dialogue Dataset Automatically Constructed from Live Streaming

Open-domain dialogue systems have made promising progress in recent year...