17 citations · 40 across the 28 of their papers we have counts for
29 papers
Agentic Video Understanding: A Survey
Xinyu Deng, Siwen Luo, Daochang Liu
As large language models (LLMs) become capable of processing increasingly diverse modalities and longer temporal contexts, an emerging line of work is moving beyond fixed video-lan…
WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-Resolution
Tayyab Nasir, Daochang Liu, Ajmal Mian
Guided depth super-resolution (GDSR) typically extracts RGB guidance features through convolutional hierarchies, inheriting their fine-to-coarse bias. Thus, low-level spatial cues…
StellaVLA: In-Context Structured Demonstration for Generalizable Vision-Language-Action Models
Siyu Xu, Yunke Wang, Zijian Wang +6
Vision-Language-Action (VLA) models can follow instructions and manipulate objects, but their performance often collapses out of distribution (OOD), when the scene, viewpoint, or o…
Locating Failure in Multi-Page Visually Rich Document Understanding Systems: An Empirical Attribution
Lewei Xu, Yihao Ding, Zihan Xu +5
Multi-page visually rich document understanding (MP-VRDU) systems can fail when evidence is not faithfully represented, not selected, or not used correctly, yet final accuracy alon…
Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control
Nhat Le, Daochang Liu, Anh Nguyen +1
We present MSCoT, a multi-scale, coarse-to-fine model for test-time human motion synthesis and control. Unlike recent approaches that rely on multiple iterative denoising/token-pre…
NAIMA: Semantics Aware RGB Guided Depth Super-Resolution
Tayyab Nasir, Daochang Liu, Ajmal Mian
Guided depth super-resolution (GDSR) is a multi-modal approach for depth map super-resolution that relies on a low-resolution depth map and a high-resolution RGB image to restore f…
Draft-and-Target Sampling for Video Generation Policy
Qikang Zhang, Yingjie Lei, Wei Liu +1
Video generation models have been used as a robot policy to predict the future states of executing a task conditioned on task description and observation. Previous works ignore the…
Implicit Neural Representation-Based Continuous Single Image Super-Resolution: An Empirical Benchmark
Tayyab Nasir, Daochang Liu, Ajmal Mian
Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). However, no systematic empirical study has examined the eff…
Rest2Visual: Predicting Visually Evoked fMRI from Resting-State Scans
Chuyang Zhou, Ziao Ji, Daochang Liu +3
Understanding how spontaneous brain activity relates to stimulus-driven neural responses is a fundamental challenge in cognitive neuroscience. While task-based functional magnetic…
Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility
Yutong Hao, Chen Chen, Ajmal Saeed Mian +2
Diffusion models can generate realistic videos, but existing methods rely on implicitly learning physical reasoning from large-scale text-video datasets, which is costly, difficult…
Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance
Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh +4
Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies betwe…
Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
Chen Chen, Daochang Liu, Mubarak Shah +1
Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set image…
Generative Physical AI in Vision: A Survey
Daochang Liu, Junyu Zhang, Anh-Dung Dinh +5
Generative Artificial Intelligence (AI) has rapidly advanced the field of computer vision by enabling machines to create and interpret visual data with unprecedented sophistication…
Investigating Memorization in Video Diffusion Models
Chen Chen, Enhuai Liu, Daochang Liu +2
Diffusion models, widely used for image and video generation, face a significant limitation: the risk of memorizing and reproducing training data during inference, potentially gene…
Exploring Local Memorization in Diffusion Models via Bright Ending Attention
Chen Chen, Daochang Liu, Mubarak Shah +1
Text-to-image diffusion models have achieved unprecedented proficiency in generating realistic images. However, their inherent tendency to memorize and replicate training data duri…
Compress Guidance in Conditional Diffusion Sampling
Anh-Dung Dinh, Daochang Liu, Chang Xu
We found that enforcing guidance throughout the sampling process is often counterproductive due to the model-fitting issue, where samples are 'tuned' to match the classifier's para…
Surgical Triplet Recognition via Diffusion Model
Daochang Liu, Axel Hu, Mubarak Shah +1
Surgical triplet recognition is an essential building block to enable next-generation context-aware operating rooms. The goal is to identify the combinations of instruments, verbs,…
Towards Memorization-Free Diffusion Models
Chen Chen, Daochang Liu, Chang Xu
Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature. The users,…
CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V
Siyu Xu, Yunke Wang, Daochang Liu +2
Recent advancements in generative AI have suggested that by taking visual prompts, GPT-4V can demonstrate significant proficiency in visual recognition tasks. Despite its impressiv…
Efficient Transfer Learning in Diffusion Models via Adversarial Noise
Xiyu Wang, Baijiong Lin, Daochang Liu +1
Diffusion Probabilistic Models (DPMs) have demonstrated substantial promise in image generation tasks but heavily rely on the availability of large amounts of training data. Previo…
Boosting Diffusion Models with an Adaptive Momentum Sampler
Xiyu Wang, Anh-Dung Dinh, Daochang Liu +1
Diffusion probabilistic models (DPMs) have been shown to generate high-quality images without the need for delicate adversarial training. However, the current sampling process in D…
Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection
Chuyang Zhou, Jiajun Huang, Daochang Liu +4
Facial forgery detection is a crucial but extremely challenging topic, with the fast development of forgery techniques making the synthetic artefact highly indistinguishable. Prior…
Calibrating a Deep Neural Network with Its Predecessors
Linwei Tao, Minjing Dong, Daochang Liu +2
Confidence calibration - the process to calibrate the output probability distribution of neural networks - is essential for safety-critical applications of such networks. Recent wo…
Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
Zunzhi You, Daochang Liu, Bohyung Han +1
Recent advancements in masked image modeling (MIM) have made it a prevailing framework for self-supervised visual representation learning. The MIM pretrained models, like most deep…