Ram Nevatia

University of Southern California — United States

Computer Science · Physical Sciences

55h-index12.4kcitations222works7.22yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(89), Video Surveillance and Tracking Methods(71), Multimodal Machine Learning Applications(59), Advanced Image and Video Retrieval Techniques(47), Domain Adaptation and Few-Shot Learning(34)

Publications222 total

CaesarNeRF: Calibrated Semantic Representation for Few-Shot Generalizable Neural Rendering
Lecture notes in computer science·2024· 1 cited
BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models
arXiv (Cornell University)·2024Open Access
SEAS: ShapE-Aligned Supervision for Person Re-Identification
2024· 12 cited
Large Language Models are Good Prompt Learners for Low-Shot Image Classification
2024· 10 cited
GaitSTR: Gait Recognition With Sequential Two-Stream Refinement
IEEE Transactions on Biometrics Behavior and Identity Science·2024· 13 cited
GaitSTR: Gait Recognition with Sequential Two-stream Refinement
arXiv (Cornell University)·2024· 1 citedOpen Access
Efficient Feature Distillation for Zero-shot Annotation Object Detection
2024· 4 cited
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
2024· 12 cited
Leveraging Task-Specific Pre-Training to Reason across Images and Videos
2024
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
2024· 9 cited
ShARc: Shape and Appearance Recognition for Person Identification In-the-wild
2024· 17 cited
Large Language Models are Good Prompt Learners for Low-Shot Image Classification
arXiv (Cornell University)·2023Open Access
CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering
arXiv (Cornell University)·2023Open Access
ShARc: Shape and Appearance Recognition for Person Identification In-the-wild
arXiv (Cornell University)·2023Open Access
GaitRef: Gait Recognition with Refined Sequential Skeletons
2023· 28 cited
AG-ReID 2023: Aerial-Ground Person Re-identification Challenge Results
2023· 6 cited
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
arXiv (Cornell University)·2023· 3 citedOpen Access
CAT-NeRF: Constancy-Aware Tx<sup>2</sup>Former for Dynamic Body Modeling
2023· 4 cited
Multimodal Neural Radiance Field
2023· 13 cited
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
arXiv (Cornell University)·2023Open Access
page 1 of 12Next →

Frequent Co-authors

Jiyang Gao(10), Zhenheng Yang(8), Bo Wu(7), Chen Sun(5), Kan Chen(5), Gérard Medioni(5), Chang Huang(4), Bo Yang(4), Tal Hassner(4), Iacopo Masi(4), Somboon Hongeng(3), Peng Wang(3), Wei Xu(3), Jongmoo Choi(3), Feng-Ju Chang(3), Chen Sun(2), Tao Zhao(2), François Brémond(2), Jiang Wang(2), Runzhou Ge(2)