236 citations · 287 across the 12 of their papers we have counts for
12 papers
Return of Unconditional Generation: A Self-supervised Representation Generation Method
Tianhong Li, Dina Katabi, Kaiming He
Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models…
Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
Tianhong Li, Sangnie Bhardwaj, Yonglong Tian +6
Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalization capabilities. However, automatically…
Reparo: Loss-Resilient Generative Codec for Video Conferencing
Tianhong Li, Vibhaalakshmi Sivaraman, Pantea Karimi +3
Packet loss during video conferencing often results in poor quality and video freezing. Retransmitting lost packets is often impractical due to the need for real-time playback, and…
MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
Tianhong Li, Huiwen Chang, Shlok Kumar Mishra +3
Generative modeling and representation learning are two key tasks in computer vision. However, these models are typically trained independently, which ignores the potential for eac…
Unsupervised Learning for Human Sensing Using Radio Signals
Tianhong Li, Lijie Fan, Yuan Yuan +1
There is a growing literature demonstrating the feasibility of using Radio Frequency (RF) signals to enable key computer vision tasks in the presence of occlusions and poor lightin…
Targeted Supervised Contrastive Learning for Long-Tailed Recognition
Tianhong Li, Peng Cao, Yuan Yuan +5
Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of…
Addressing Feature Suppression in Unsupervised Visual Representations
Tianhong Li, Lijie Fan, Yuan Yuan +5
Contrastive learning is one of the fastest growing research areas in machine learning due to its ability to learn useful representations without labeled data. However, contrastive…
In-Home Daily-Life Captioning Using Radio Signals
Lijie Fan, Tianhong Li, Yuan Yuan +1
This paper aims to caption daily life --i.e., to create a textual description of people's activities and interactions with objects in their homes. Addressing this problem requires…
Learning Longterm Representations for Person Re-Identification Using Radio Signals
Lijie Fan, Tianhong Li, Rongyao Fang +3
Person Re-Identification (ReID) aims to recognize a person-of-interest across different places and times. Existing ReID methods rely on images or videos collected using RGB cameras…
Making the Invisible Visible: Action Recognition Through Walls and Occlusions
Tianhong Li, Lijie Fan, Mingmin Zhao +2
Understanding people's actions and interactions typically depends on seeing them. Automating the process of action recognition from visual data has been the topic of much research…
Multi-Scale Dense Networks for Resource Efficient Image Classification
Gao Huang, Danlu Chen, Tianhong Li +3
In this paper we investigate image classification with computational resource limits at test time. Two such settings are: 1. anytime classification, where the network's prediction…
Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes
Lunjia Hu, Ruihan Wu, Tianhong Li +1
In this work we study the quantitative relation between the recursive teaching dimension (RTD) and the VC dimension (VCD) of concept classes of finite sizes. The RTD of a concept c…