Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Zha, Kaiwen"'
Autor:
Zha, Kaiwen, Yu, Lijun, Fathi, Alireza, Ross, David A., Schmid, Cordelia, Katabi, Dina, Gu, Xiuye
Image tokenization, the process of transforming raw image pixels into a compact low-dimensional latent representation, has proven crucial for scalable and efficient image generation. However, mainstream image tokenization methods generally have limit
Externí odkaz:
http://arxiv.org/abs/2412.05796
Autor:
Zha, Kaiwen
Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. Howeve
Deep regression models typically learn in an end-to-end fashion without explicitly emphasizing a regression-aware representation. Consequently, the learned representations exhibit fragmentation and fail to capture the continuous nature of sample orde
Externí odkaz:
http://arxiv.org/abs/2210.01189
Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning attacks of co
Externí odkaz:
http://arxiv.org/abs/2202.11202
In this work, we study the image transformation problem, which targets at learning the underlying transformations (e.g., the transition of seasons) from a collection of unlabeled images. However, there could be countless of transformations in the rea
Externí odkaz:
http://arxiv.org/abs/2103.07751
Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. Howeve
Externí odkaz:
http://arxiv.org/abs/2102.09554
Publikováno v:
Nat Mach Intell 2, 24-253 (2020)
Understanding sequential information is a fundamental task for artificial intelligence. Current neural networks attempt to learn spatial and temporal information as a whole, limited their abilities to represent large scale spatial representations ove
Externí odkaz:
http://arxiv.org/abs/2006.00212
Publikováno v:
In Applied Catalysis A, General 25 September 2023 666
Extracting temporal and representation features efficiently plays a pivotal role in understanding visual sequence information. To deal with this, we propose a new recurrent neural framework that can be stacked deep effectively. There are mainly two n
Externí odkaz:
http://arxiv.org/abs/1811.09961
We introduce the first benchmark for a new problem --- recognizing human action adverbs (HAA): "Adverbs Describing Human Actions" (ADHA). This is the first step for computer vision to change over from pattern recognition to real AI. We demonstrate so
Externí odkaz:
http://arxiv.org/abs/1802.01144