activity
20182025
most citedBounds all around: training energy-based models with bidirectional bounds

5 citations · 9 across the 7 of their papers we have counts for

collaborators

15 papers

cs.LG2025

Exploring bidirectional bounds for minimax-training of Energy-based models

Cong Geng, Jia Wang, Li Chen +3

Energy-based models (EBMs) estimate unnormalized densities in an elegant framework, but they are generally difficult to train. Recent work has linked EBMs to generative adversarial…

cs.CV2022

Enhanced Deep Animation Video Interpolation

Wang Shen, Cheng Ming, Wenbo Bao +3

Existing learning-based frame interpolation algorithms extract consecutive frames from high-speed natural videos to train the model. Compared to natural videos, cartoon videos are…

eess.IV2022

A Coding Framework and Benchmark towards Low-Bitrate Video Understanding

Yuan Tian, Guo Lu, Yichao Yan +3

Video compression is indispensable to most video analysis systems. Despite saving transportation bandwidth, it also deteriorates downstream video understanding tasks, especially at…

cs.LG2021★ 5 cited

Bounds all around: training energy-based models with bidirectional bounds

Cong Geng, Jia Wang, Zhiyong Gao +2

Energy-based models (EBMs) provide an elegant framework for density estimation, but they are notoriously difficult to train. Recent work has established links to generative adversa…

cs.CV2021

Self-Conditioned Probabilistic Learning of Video Rescaling

Yuan Tian, Guo Lu, Xiongkuo Min +4

Bicubic downscaling is a prevalent technique used to reduce the video storage burden or to accelerate the downstream processing speed. However, the inverse upscaling step is non-tr…

cs.CV2021

EAN: Event Adaptive Network for Enhanced Action Recognition

Yuan Tian, Yichao Yan, Guangtao Zhai +2

Efficiently modeling spatial-temporal information in videos is crucial for action recognition. To achieve this goal, state-of-the-art methods typically employ the convolution opera…