the-decoder

ByteDance's StoryMem gives AI video models a memory so characters stop shapeshifting between scenes

Researchers from ByteDance and Nanyang Technological University have developed StoryMem, a system designed to maintain visual consistency in AI-generated videos across multiple scenes. The system ...
Salon

Deepfake videos explained: What they are and how to identify them

A “deepfake” is a video created using artificial intelligence (AI) showing real people doing and saying things they never did. The first iterations of deepfakes appeared in pornography when ...
GitHub

Controllable Human-centric Keyframe Interpolation with Generative Prior

We introduce PoseFuse3D Keyframe Interpolator (PoseFuse3D-KI), a novel framework that integrates 3D human guidance signals into the diffusion process for Controllable Human-centric Keyframe ...
IEEE

A Tightly-Coupled and Keyframe-Based Visual-Inertial-Lidar Odometry System for UGVs With Adaptive Sensor Reliability Evaluation

Abstract: In this article, a novel visual-inertial-lidar odometry (VILO) system named TCK-VILO is proposed to assist unmanned ground vehicles in reaching high localization performance. We introduce an ...
IEEE

Augmenting the Robustness and Efficiency of Violence Detection Systems for Surveillance and Non-Surveillance Scenarios

Abstract: Violence detection holds immense significance in ensuring public safety, security, and law enforcement in various domains. With the increasing availability of video data from surveillance ...