37 citations · 42 across the 9 of their papers we have counts for
10 papers · 1 filter
Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion
Mang Ning, Mingxiao Li, Le Zhang +4
In this paper, we study the diffusability (learnability) of variational autoencoders (VAE) in latent diffusion. First, we show that pixel-space diffusion trained with an MSE object…
DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
Mang Ning, Mingxiao Li, Jianlin Su +6
This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosin…
Representation Learning and Identity Adversarial Training for Facial Behavior Understanding
Mang Ning, Albert Ali Salah, Itir Onal Ertugrul
Facial Action Unit (AU) detection has gained significant attention as it enables the breakdown of complex facial expressions into individual muscle movements. In this paper, we rev…
Snakes and Ladders: Two Steps Up for VideoMamba
Hui Lu, Albert Ali Salah, Ronald Poppe
Video understanding requires the extraction of rich spatio-temporal representations, which transformer models achieve through self-attention. Unfortunately, self-attention poses a…
Enhancing Video Transformers for Action Understanding with VLM-aided Training
Hui Lu, Hu Jian, Ronald Poppe +1
Owing to their ability to extract relevant spatio-temporal video embeddings, Vision Transformers (ViTs) are currently the best performing models in video action understanding. Howe…
TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions
Hui Lu, Albert Ali Salah, Ronald Poppe
A key challenge in continuous sign language recognition (CSLR) is to efficiently capture long-range spatial interactions over time from the video input. To address this challenge,…