Object Detection
Object detection, a core computer vision task, aims to identify and locate objects within images or videos. Current research emphasizes improving accuracy and efficiency across diverse scenarios, focusing on architectures like YOLO and DETR, and exploring techniques such as multimodal fusion, attention mechanisms, and loss function refinements to handle challenges like small object detection, adverse weather conditions, and limited labeled data. These advancements have significant implications for applications ranging from autonomous driving and robotics to medical image analysis and remote sensing, driving progress in both theoretical understanding and practical deployment of object detection systems.
Papers
Humans need not label more humans: Occlusion Copy & Paste for Occluded Human Instance Segmentation
Evan Ling, Dezhao Huang, Minhoe Hur
Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking
Alan Lukezic, Ziga Trojer, Jiri Matas, Matej Kristan
PS-ARM: An End-to-End Attention-aware Relation Mixer Network for Person Search
Mustansar Fiaz, Hisham Cholakkal, Sanath Narayan, Rao Muhammad Anwer, Fahad Shahbaz Khan