16 citations · 43 across the 14 of their papers we have counts for
16 papers
TRACER: A Multimodal Harness for Patient Care in Hospitals
Zane Durante, Paul Tang, Keshigeyan Chandrasegaran +11
Continuous video and clinical records provide complementary information for understanding how patient behavior evolves over a hospital stay. A central challenge is how to represent…
GPIC: A Giant Permissive Image Corpus for Visual Generation
Keshigeyan Chandrasegaran, Kyle Sargent, Suchir Agarwal +6
Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image Corpus of approximately 28 tri…
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
Pingyue Zhang, Zihan Huang, Yue Wang +11
Spatial embodied intelligence requires agents to act to acquire information under partial observability. While multimodal foundation models excel at passive perception, their capac…
Exploring Diffusion Transformer Designs via Grafting
Keshigeyan Chandrasegaran, Michael Poli, Daniel Y. Fu +9
Designing model architectures requires decisions such as selecting operators (e.g., attention, convolution) and configurations (e.g., depth, width). However, evaluating the impact…
MindCube: Spatial Mental Modeling from Limited Views
Qineng Wang, Baiqiao Yin, Pingyue Zhang +11
Can Vision-Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form spatial mental models naturally, internal representations of unseen spac…
T*: Re-thinking Temporal Search for Long-Form Video Understanding
Jinhui Ye, Zihan Wang, Haosen Sun +9
Efficiently understanding long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding…
HourVideo: 1-Hour Video-Language Understanding
Keshigeyan Chandrasegaran, Agrim Gupta, Lea M. Hadzic +7
We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, track…
Model Inversion Robustness: Can Transfer Learning Help?
Sy-Tuyen Ho, Koh Jun Hao, Keshigeyan Chandrasegaran +2
Model Inversion (MI) attacks aim to reconstruct private training data by abusing access to machine learning models. Contemporary MI attacks have achieved impressive attack performa…
Label-Only Model Inversion Attacks via Knowledge Transfer
Ngoc-Bao Nguyen, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +1
In a model inversion (MI) attack, an adversary abuses access to a machine learning (ML) model to infer and reconstruct private training data. Remarkable progress has been made in t…
A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot
Milad Abdollahzadeh, Guimeng Liu, Touba Malekzadeh +3
Generative modeling in machine learning aims to synthesize new data samples that are statistically similar to those observed during training. While conventional generative models s…
AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation
Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +5
Few-shot image generation (FSIG) aims to learn to generate new and diverse images given few (e.g., 10) training samples. Recent work has addressed FSIG by leveraging a GAN pre-trai…
Re-thinking Model Inversion Attacks Against Deep Neural Networks
Ngoc-Bao Nguyen, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +1
Model inversion (MI) attacks aim to infer and reconstruct private training data by abusing access to a model. MI attacks have raised concerns about the leaking of sensitive informa…
Few-shot Image Generation via Adaptation-Aware Kernel Modulation
Yunqing Zhao, Keshigeyan Chandrasegaran, Milad Abdollahzadeh +1
Few-shot image generation (FSIG) aims to learn to generate new and diverse samples given an extremely limited number of samples from a domain, e.g., 10 training samples. Recent wor…
Discovering Transferable Forensic Features for CNN-generated Images Detection
Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Alexander Binder +1
Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods. Though detection of such counterfe…
Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?
Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Yunqing Zhao +1
This work investigates the compatibility between label smoothing (LS) and knowledge distillation (KD). Contemporary findings addressing this thesis statement take dichotomous stand…
A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection
Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Ngai-Man Cheung
CNN-based generative modelling has evolved to produce synthetic images indistinguishable from real images in the RGB pixel space. Recent works have observed that CNN-generated imag…