Automated crowd counting in Hajj video is difficult not because current models lack capacity, but because the footage violates the assumptions those models were built on: cameras observe the crowd from steep, near-vertical angles, individuals occlude one another extensively, and a single frame can contain well over a thousand people. Benchmarks that test crowd counting in such an environment are either private or not detailed per second.
arXiv:2607. 07322v1 Announce Type: cross Abstract: Automated crowd counting in Hajj video is difficult not because current models lack capacity, but because the footage violates the assumptions those models were built on: cameras observe the crowd from steep, near-vertical angles, individuals occlude one another extensively, and a single frame can contain well over a thousand people.
By Reem AlYabis, Fares AlTuwaim, AlJawharh AlOtaibi, Mohamed Eltahir
arXiv:2606. 30215v1 Announce Type: cross Abstract: RGB-T detectors leverage the complementary strengths of visible and thermal infrared modalities, achieving robust performance under challenging conditions.
By Chao Tian, Zikun Zhou, Chao Yang, Guoqing Zhu, Zhenyu He
ABACUS is a unified vision-language model that handles object counting, crowd counting, referring-expression counting, and count-faithful image generation without any benchmark-specific training required. Our model is built on existing 3B-parameter unified foundation model and is adapted for object localization tasks using three key innovations: density-aware adaptive zooming with objectness maps for spatial grounding; a boundary-aware count policy via GRPO to eliminate crop-boundary errors; and a cycle-consistent GRPO strategy where the understanding branch self-critiques generated outputs, closing the understanding-generation gap without any external annotations.
arXiv:2607. 01759v1 Announce Type: cross Abstract: Open-vocabulary object detection aims to localize and classify objects beyond the fixed set of categories seen dur ing training.
By Jae-Ryung Hong, Ho-Joong Kim, Seong-Whan Lee
arXiv:2608. 03096v1 Announce Type: cross Abstract: Recent advances in video generation models have significantly intensified the deepfake threat, yet the current deepfake video detection benchmarks remain underdeveloped.
By Pei Li, Sihan Chen, Delong Ran, Tianshuo Cong
Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task setting of unsupervised VPS, omitting any human supervision.
Recent advances in video generation models have significantly intensified the deepfake threat, yet the current deepfake video detection benchmarks remain underdeveloped. In particular, the effectiveness of image-level detectors in the video domain has not been systematically assessed.
arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
By Sicheng Zuo, Zixun Xie, Wenzhao Zheng, Shaoqing Xu, Fang Li, Shengyin Jiang, Long Chen, Zhi-Xin Yang, Jiwen Lu
arXiv:2607. 17754v1 Announce Type: cross Abstract: In logistics automation, precise segmentation of unseen objects is crucial for efficient robotic manipulation in cluttered environments.
By Yesol Park, Hye-Jung Yoon, Juno Kim, Byoung-Tak Zhang
arXiv:2403. 09281v3 Announce Type: cross Abstract: We propose CLIP-EBC, the first fully CLIP-based model for accurate crowd density estimation.
By Yiming Ma, Victor Sanchez, Tanaya Guha
arXiv:2607. 13421v1 Announce Type: cross Abstract: Spatio-Temporal Video Grounding (STVG) aims to retrieve the visual trajectory of a specific object from a video stream as described by a natural language expression.
By Kai Chen, Ming Dai, Wenxuan Cheng, Wankou Yang