Thakare Kamalakar Vijay

Orcid: 0000-0003-4587-4126

Affiliations:
  • Indian Institute of Technology Bhubaneswar, School of Electrical Sciences, Odisha, India


According to our database1, Thakare Kamalakar Vijay authored at least 15 papers between 2021 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of five.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
IMPACT: Interpretable Most Important Person Analysis and Classification using Transformer-based Models.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

VAST-ReID: A Low-Light Benchmark Dataset for Person Re-Identification with Visual and Attribute-Rich Semantic Tracking.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026

Group Emotion Recognition Explained! A Human-Centric Approach Using Multi-Modal VGER Dataset and Framework.
Proceedings of the 21st International Conference on Computer Vision Theory and Applications, 2026

PairAnom: A Benchmark Dataset for Pairwise Fine-Grained Multi-Class Video Anomaly Detection.
Proceedings of the 21st International Conference on Computer Vision Theory and Applications, 2026

2025
CLIPping Imbalances: A Novel Evaluation Baseline and PEARL Dataset for Pedestrian Attribute Recognition.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

Can Person-Level Attributes Improve Group Re-Identification?
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

2024
Let's Observe Them Over Time: An Improved Pedestrian Attribute Recognition Approach.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Unsupervised Annotation and Detection of Novel Objects Using Known Objectness.
Proceedings of the 19th International Joint Conference on Computer Vision, 2024

Pedestrian Attribute Recognition Using Hierarchical Transformers.
Proceedings of the Pattern Recognition - 27th International Conference, 2024

2023
RareAnom: A Benchmark Video Dataset for Rare Type Anomalies.
Pattern Recognit., August, 2023

Detection of Road Accidents Using Synthetically Generated Multi-Perspective Accident Videos.
IEEE Trans. Intell. Transp. Syst., February, 2023

DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

2022
Object Interaction-Based Localization and Description of Road Accident Events Using Deep Learning.
IEEE Trans. Intell. Transp. Syst., 2022

A multi-stream deep neural network with late fuzzy fusion for real-world anomaly detection.
Expert Syst. Appl., 2022

2021
PIDLNet: A Physics-Induced Deep Learning Network for Characterization of Crowd Videos.
Proceedings of the 17th IEEE International Conference on Advanced Video and Signal Based Surveillance, 2021


  Loading...