Rama Chellappa

48

Papers

62

Total Citations

Papers (48)

Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model

Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval

DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization

ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models

Enrich and Detect: Video Temporal Grounding with Multimodal LLMs

TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision

Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training

Class Consistent Multi-Modal Fusion With Binary Features

Matrix Completion for Resolving Label Ambiguity

Hierarchical Multimodal Metric Learning for Multimodal Classification

Learning From Synthetic Data: Addressing Domain Shift for Semantic Segmentation

Deep Density Clustering of Unconstrained Faces

Generate to Adapt: Aligning Domains Using Generative Adversarial Networks

Learning Without Memorizing

Unsupervised Domain-Specific Deblurring via Disentangled Representations

DuDoNet: Dual Domain Network for CT Metal Artifact Reduction

SAINT: Spatially Aware Interpolation NeTwork for Medical Slice Synthesis

3DRegNet: A Deep Neural Network for 3D Point Registration

Hierarchical Video Prediction Using Relational Layouts for Human-Object Interactions

HyperSegNAS: Bridging One-Shot Neural Architecture Search With 3D Medical Image Segmentation Using HyperNet

EyePAD++: A Distillation-Based Approach for Joint Eye Authentication and Presentation Attack Detection Using Periocular Images

Segment and Complete: Defending Object Detectors Against Adversarial Patch Attacks With Robust Patch Detection

HaLP: Hallucinating Latent Positives for Skeleton-Based Self-Supervised Learning of Actions

SSH: Single Stage Headless Face Detector

Soft-NMS -- Improving Object Detection With One Line of Code

Uncertainty Modeling of Contextual-Connections Between Tracklets for Unconstrained Video-Based Face Recognition

A Dual-Path Model With Adaptive Attention for Vehicle Re-Identification

Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation

PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition

The Pursuit of Knowledge: Discovering and Localizing Novel Categories Using Dual Memory

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

MOST: Multiple Object Localization with Self-Supervised Transformers for Object Discovery

SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining

STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos

The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification

Visual Question Answering on Image Sets

Where in the World Is This Image? Transformer-Based Geo-Localization in the Wild

Disentangling 3D Pose in a Dendritic CNN for Unconstrained 2D Face Alignment

Medical World Model

FaceXFormer: A Unified Transformer for Facial Analysis

MetaReg: Towards Domain Generalization using Meta-Regularization

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

FeLMi : Few shot Learning with hard Mixup

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs