ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Amit K. Roy-Chowdhury

Amit K. Roy-Chowdhury

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 14, 2026, 11:22 PM AMS

22

papers

630

total citations

papers (22)

Unsupervised Multi-Source Domain Adaptation Without Access to Source Data

Domain Adaptive Semantic Segmentation Using Weak Labels

Spatio-Temporal Representation Factorization for Video-Based Person Re-Identification

Unbiased Scene Graph Generation in Videos

Controllable Dynamic Multi-Task Architectures

Multi-Expert Adversarial Attack Detection in Person Re-Identification Using Context Inconsistency

Camera On-Boarding for Person Re-Identification Using Hypothesis Transfer Learning

Zero-Query Transfer Attacks on Context-Aware Object Detectors

Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes

Non-Adversarial Video Synthesis With Learned Priors

Cross-Modal Knowledge Transfer without Task-Relevant Source Data

Prior-guided Source-free Domain Adaptation for Human Pose Estimation

Towards a Universal Synthetic Video Detector: From Face or Background Manipulations to Fully AI-Generated Content

Exploiting Temporal Coherence for Self-Supervised One-shot Video Re-identification

SUMMIT: Source-Free Adaptation of Uni-Modal Models to Multi-Modal Targets

Efficient Controllable Multi-Task Architectures

Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning

Towards Source-Free Machine Unlearning

Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models

Conformal Prediction and MLLM aided Uncertainty Quantification in Scene Graph Generation

Text-Based Temporal Localization of Novel Events

AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments