New methods improve how self-driving cars perceive their surroundings.
Xiaohu Lu, Hayder Radha
― 5 min read
Computer Science - Computer Vision and Pattern Recognition
RSSLatest Articles
A groundbreaking model links images and text, enhancing information retrieval.
Andreas Koukounas, Georgios Mastrapas, Bo Wang
― 7 min read
External memory banks enhance diffusion models for better image and sound creation.
Yi Tang, Peng Sun, Zhenglin Cheng
― 6 min read
A new method improves how models process visual information efficiently.
Ke Wang, Hong Xuan
― 7 min read
Task fingerprinting could transform knowledge sharing in medical imaging.
Patrick Godau, Akriti Srivastava, Tim Adler
― 5 min read
A proactive method using Vision Language Models aims to detect hidden backdoor attacks.
Kyle Stein, Andrew Arash Mahyari, Guillermo Francia
― 7 min read
Research reveals new benchmark for improving AI's grasp of geometry.
Jiarui Zhang, Ollie Liu, Tianyu Yu
― 4 min read
Explore the new VisionArena dataset enhancing AI interactions with real user chats.
Christopher Chou, Lisa Dunlap, Koki Mashita
― 5 min read
StreamChat transforms how we engage with streaming video in real-time.
Jihao Liu, Zhiding Yu, Shiyi Lan
― 7 min read
Discover a faster, easier method for 3D mesh editing that boosts creativity.
Will Gao, Dilin Wang, Yuchen Fan
― 5 min read
Learn how FPA improves image generation from text descriptions quickly and accurately.
Khalil Mrini, Hanlin Lu, Linjie Yang
― 6 min read
This new method streamlines image editing using text commands.
Vladimir Kulikov, Matan Kleiner, Inbar Huberman-Spiegelglas
― 6 min read
Advanced technology bridges the gap between design and garment creation.
Feng Zhou, Ruiyang Liu, Chen Liu
― 5 min read
Discover how ASDnB enhances speaker detection through body language and facial cues.
Tiago Roxo, Joana C. Costa, Pedro Inácio
― 8 min read
AI robots learn navigation through real-world indoor videos to enhance their movement.
Mingfei Han, Liang Ma, Kamila Zhumakhanova
― 7 min read
SAM-Mix improves medical image analysis, reducing manual work and enhancing accuracy.
Tyler Ward, Abdullah-Al-Zubaer Imran
― 7 min read
See clothes like never before with flat images for online shopping.
Ioannis Xarchakos, Theodoros Koukopoulos
― 7 min read
Discover a new method for creating visual programs quickly and cheaply.
Michal Shlapentokh-Rothman, Yu-Xiong Wang, Derek Hoiem
― 4 min read
A new tool combining satellite and ground images for better land mapping.
Pallavi Jain, Dino Ienco, Roberto Interdonato
― 7 min read
A new approach combines neural fields and deformation models for detailed 3D motion capture.
Aymen Merrouche, Stefanie Wuhrer, Edmond Boyer
― 6 min read
A deep dive into how computers identify human actions with objects.
Mingda Jia, Liming Zhao, Ge Li
― 7 min read
Learn how combining text and images enhances sentiment analysis.
Nguyen Van Doan, Dat Tran Nguyen, Cam-Van Thi Nguyen
― 6 min read
Discover how self-supervised learning changes Alzheimer's detection in brain imaging.
Hao-Chun Yang, Sicheng Dai, Saige Rutherford
― 6 min read
New tech generates realistic images of people with ease.
Zijian Zhou, Shikun Liu, Xiao Han
― 6 min read
Discover how CAT improves machine learning with innovative data strategies.
Sumaiya Zoha, Jeong-Gun Lee, Young-Woong Ko
― 7 min read
Discover how POINTS1.5 enhances image and text processing capabilities.
Yuan Liu, Le Tian, Xiao Zhou
― 6 min read
WavFusion combines audio, text, and visuals for better emotion recognition.
Feng Li, Jiusong Luo, Wanjun Xia
― 6 min read
LOMA combines visual and language features for improved 3D space predictions.
Yubo Cui, Zhiheng Li, Jiaqiang Wang
― 6 min read
A new framework enhances data labeling for self-driving cars.
Yushan Han, Hui Zhang, Honglei Zhang
― 6 min read
New methods improve video predictions using less data.
Gaurav Shrivastava, Abhinav Shrivastava
― 6 min read
ALoRE optimizes model training for efficient image recognition and broader applications.
Sinan Du, Guosheng Zhang, Keyao Wang
― 7 min read
How 3D occupancy prediction is shaping autonomous vehicle technology.
Bohan Li, Xin Jin, Jiajun Deng
― 6 min read
Innovative DMIC framework improves person recognition across different camera types.
Yiming Yang, Weipeng Hu, Haifeng Hu
― 6 min read
A new method to evaluate AI's image and video generation using scene graphs.
Ziqi Gao, Weikai Huang, Jieyu Zhang
― 6 min read
TextRefiner boosts Vision-Language Models' performance, making them faster and more accurate.
Jingjing Xie, Yuxin Zhang, Jun Peng
― 7 min read
Learn how to prevent model collapse in generative models using real data.
Huminhao Zhu, Fangyikang Wang, Tianyu Ding
― 6 min read
Discover how visual illusions impact VQA models and their performance.
Mohammadmostafa Rostamkhani, Baktash Ansari, Hoorieh Sabzevari
― 6 min read
AsyncDSB offers a smarter way to restore damaged images creatively.
Zihao Han, Baoquan Zhang, Lisai Zhang
― 6 min read
Learn how lightweight AI models retain knowledge efficiently.
Jiaming Lv, Haoyuan Yang, Peihua Li
― 6 min read
Discover how visual-language models connect images and text for smarter machines.
Quang-Hung Le, Long Hoang Dang, Ngan Le
― 7 min read