36 citations · 194 across the 34 of their papers we have counts for
36 papers
Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval
Arun Reddy, Alexander Martin, Eugene Yang +7
In this work, we tackle the problem of text-to-video retrieval (T2VR). Inspired by the success of late interaction techniques in text-document, text-image, and text-video retrieval…
Weighted Risk Invariance: Domain Generalization under Invariant Feature Shift
Gina Wong, Joshua Gleason, Rama Chellappa +2
Learning models whose predictions are invariant under multiple environments is a promising approach for out-of-distribution generalization. Such models are trained to extract featu…
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
Micah Goldblum, Hossein Souri, Renkun Ni +10
Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an…
Whole-body Detection, Recognition and Identification at Altitude and Range
Siyuan Huang, Ram Prabhakar Kathirvel, Chun Pong Lau +1
In this paper, we address the challenging task of whole-body biometric detection, recognition, and identification at distances of up to 500m and large pitch angles of up to 50 degr…
Learning to Prompt Your Domain for Vision-Language Models
Guoyizhe Wei, Feng Wang, Anshul Shah +1
Prompt learning has recently become a very efficient transfer learning paradigm for Contrastive Language Image Pretraining (CLIP) models. Compared with fine-tuning the entire encod…
Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization
Mahyar Fazlyab, Taha Entesari, Aniket Roy +1
To improve the robustness of deep classifiers against adversarial perturbations, many approaches have been proposed, such as designing new architectures with better robustness prop…
ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
Qiao Gu, Alihusein Kuwajerwala, Sacha Morin +13
For robots to perform a wide variety of tasks, they require a 3D representation of the world that is semantically rich, yet compact and efficient for task-driven perception and pla…
EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone
Shraman Pramanick, Yale Song, Sayan Nag +5
Video-language pre-training (VLP) has become increasingly important due to its ability to generalize to various vision and language tasks. However, existing egocentric VLP framewor…
SMC-UDA: Structure-Modal Constraint for Unsupervised Cross-Domain Renal Segmentation
Zhusi Zhong, Jie Li, Lulu Bi +6
Medical image segmentation based on deep learning often fails when deployed on images from a different domain. The domain adaptation methods aim to solve domain-shift challenges, b…
Attribute-Guided Encryption with Facial Texture Masking
Chun Pong Lau, Jiang Liu, Rama Chellappa
The increasingly pervasive facial recognition (FR) systems raise serious concerns about personal privacy, especially for billions of users who have publicly shared their photos on…
DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection
Jiang Liu, Chun Pong Lau, Zhongliang Guo +3
The increasingly pervasive facial recognition (FR) systems raise serious concerns about personal privacy, especially for billions of users who have publicly shared their photos on…
The 7th AI City Challenge
Milind Naphade, Shuo Wang, David C. Anastasiu +17
The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence - retail business and Intelligent Traffic Systems…
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
Anshul Shah, Aniket Roy, Ketul Shah +4
Supervised learning of skeleton sequence encoders for action recognition has received significant attention in recent times. However, learning such encoders without labels continue…
Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances
Arun V. Reddy, Ketul Shah, William Paul +6
Human action recognition is a challenging problem, particularly when there is high variability in factors such as subject appearance, backgrounds and viewpoint. While deep neural n…
STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos
Anshul Shah, Benjamin Lundell, Harpreet Sawhney +1
We address the problem of extracting key steps from unlabeled procedural videos, motivated by the potential of Augmented Reality (AR) headsets to revolutionize job training and per…
Thinking Two Moves Ahead: Anticipating Other Users Improves Backdoor Attacks in Federated Learning
Yuxin Wen, Jonas Geiping, Liam Fowl +4
Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the…
DA-VSR: Domain Adaptable Volumetric Super-Resolution For Medical Images
Cheng Peng, S. Kevin Zhou, Rama Chellappa
Medical image super-resolution (SR) is an active research area that has many potential applications, including reducing scan time, bettering visual understanding, increasing robust…
VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment
Shraman Pramanick, Li Jing, Sayan Nag +4
Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use…
REGAS: REspiratory-GAted Synthesis of Views for Multi-Phase CBCT Reconstruction from a single 3D CBCT Acquisition
Cheng Peng, Haofu Liao, S. Kevin Zhou +1
It is a long-standing challenge to reconstruct Cone Beam Computed Tomography (CBCT) of the lung under respiratory motion. This work takes a step further to address a challenging se…
Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Prompting
Guangxing Han, Long Chen, Jiawei Ma +3
We study multi-modal few-shot object detection (FSOD) in this paper, using both few-shot visual examples and class semantic information for detection, which are complementary to ea…
Towards performant and reliable undersampled MR reconstruction via diffusion model sampling
Cheng Peng, Pengfei Guo, S. Kevin Zhou +2
Magnetic Resonance (MR) image reconstruction from under-sampled acquisition promises faster scanning time. To this end, current State-of-The-Art (SoTA) approaches leverage deep neu…
EyePAD++: A Distillation-based approach for joint Eye Authentication and Presentation Attack Detection using Periocular Images
Prithviraj Dhar, Amit Kumar, Kirsten Kaplan +3
A practical eye authentication (EA) system targeted for edge devices needs to perform authentication and be robust to presentation attacks, all while remaining compute and latency…
Max-Margin Contrastive Learning
Anshul Shah, Suvrit Sra, Rama Chellappa +1
Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence. We suspect this behavio…
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses
Chun Pong Lau, Jiang Liu, Hossein Souri +3
Adversarial training (AT) is considered to be one of the most reliable defenses against adversarial attacks. However, models trained with AT sacrifice standard accuracy and do not…