54 citations · 105 across the 11 of their papers we have counts for
12 papers
CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer
Yisen Wang, Zhirong Wu, Limin Wang
Vision Transformers (ViT) excel in semantic understanding but fail to discriminate between object instances (e.g., identical embeddings for two dogs), limiting their use in instanc…
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Jiajie Jin, Yuyang Hu, Kai Qiu +15
Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the result…
Exploring Transferability for Randomized Smoothing
Kai Qiu, Huishuai Zhang, Zhirong Wu +1
Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model ro…
NuTime: Numerically Multi-Scaled Embedding for Large-Scale Time-Series Pretraining
Chenguo Lin, Xumeng Wen, Wei Cao +4
Recent research on time-series self-supervised models shows great promise in learning semantic representations. However, it has been limited to small-scale datasets, e.g., thousand…
ClipCrop: Conditioned Cropping Driven by Vision-Language Model
Zhihang Zhong, Mingxi Cheng, Zhirong Wu +7
Image cropping has progressed tremendously under the data-driven paradigm. However, current approaches do not account for the intentions of the user, which is an issue especially w…
Bringing Rolling Shutter Images Alive with Dual Reversed Distortion
Zhihang Zhong, Mingdeng Cao, Xiao Sun +5
Rolling shutter (RS) distortion can be interpreted as the result of picking a row of pixels from instant global shutter (GS) frames over time during the exposure of the RS camera.…
A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation
Yutong Chen, Fangyun Wei, Xiao Sun +2
This paper proposes a simple transfer learning baseline for sign language translation. Existing sign language datasets (e.g. PHOENIX-2014T, CSL-Daily) contain only about 10K-20K pa…
Debiased Learning from Naturally Imbalanced Pseudo-Labels
Xudong Wang, Zhirong Wu, Long Lian +1
Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e…
Towards Tokenized Human Dynamics Representation
Kenneth Li, Xiao Sun, Zhirong Wu +2
For human action understanding, a popular research direction is to analyze short video clips with unambiguous semantic content, such as jumping and drinking. However, methods for u…
One-Shot Generative Domain Adaptation
Ceyuan Yang, Yujun Shen, Zhiyi Zhang +4
This work aims at transferring a Generative Adversarial Network (GAN) pre-trained on one image domain to a new domain referring to as few as just one target image. The main challen…
The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos
Runtao Liu, Zhirong Wu, Stella X. Yu +1
Humans can easily segment moving objects without knowing what they are. That objectness could emerge from continuous visual observations motivates us to model grouping and movement…
Aligning Pretraining for Detection via Object-Level Contrastive Learning
Fangyun Wei, Yue Gao, Zhirong Wu +2
Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrific…