Tagged articles

multimodal detection

4 articles · Page 1 of 1

Jun 16, 2026 · Artificial Intelligence

How a T‑Shaped Outfit Evades Both Visible‑Light and Thermal Detectors – Tsinghua’s New Multimodal Adversarial Method

Tsinghua researchers propose a non‑overlapping RGB‑T adversarial clothing that uses printable fabric for visible‑light patterns and aluminum film for thermal patterns, achieving over 90% attack success in digital simulations and about 60% success in real‑world tests across multiple fusion detectors.

3D modelingRGB-Tadversarial attack

0 likes · 9 min read

How a T‑Shaped Outfit Evades Both Visible‑Light and Thermal Detectors – Tsinghua’s New Multimodal Adversarial Method

Sohu Tech Products

Jul 23, 2025 · Artificial Intelligence

Boosting Video Moderation with Multimodal CLIP and Efficient Vector Search

This article describes how a video review system combines multimodal CLIP models, image‑text feature alignment, and optimized vector‑search databases such as RedisSearch and Elasticsearch to detect prohibited content in real time and perform large‑scale historical recall, while addressing challenges of generalization, storage cost, and inference speed.

.aiCLIPmodel fine-tuning

0 likes · 18 min read

Boosting Video Moderation with Multimodal CLIP and Efficient Vector Search

21CTO

Jun 28, 2021 · Artificial Intelligence

How Multimodal AI Detects Pornographic Videos: Image & Audio Fusion Explained

This article outlines a multimodal AI framework for detecting pornographic video content by combining image and audio analysis, detailing the challenges of visual and speech-based recognition, describing the DCNet and RANet model architectures, fusion strategies, and reporting experimental accuracy of 93.4% on a 3k test set.

.aiAudio ClassificationDeep Learning

0 likes · 5 min read

How Multimodal AI Detects Pornographic Videos: Image & Audio Fusion Explained

iQIYI Technical Product Team

Feb 21, 2019 · Artificial Intelligence

Multimodal Soft‑Porn Detection for Short Videos: Models, Challenges, and Lessons Learned

The article describes iQIYI's multimodal soft‑porn detection system for short videos, covering challenges like subjective definitions and class imbalance, and detailing text (Convolutional Bi‑LSTM), image (Xception‑CBAM), video (NeXtVLAD) models, integration strategies, key takeaways, and future improvements.

.aicontent moderationmultimodal detection

0 likes · 15 min read

Multimodal Soft‑Porn Detection for Short Videos: Models, Challenges, and Lessons Learned