9 papers
Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identification
Karina Kvanchiani, Timur Mamedov
The joint optimization of image-based (I2I) and text-based (T2I) person re-identification (ReID) is hindered by modality discrepancies and conflicting training objectives, leading…
Ranking vs. Assignment: The Metric Mismatch in Multi-View Object Association
Matvei Shelukhan, Timur Mamedov, Aleksandr Chukhrov +1
Multi-view object association is an important computer vision problem that underlies many multi-camera perception tasks. While this task is naturally formulated as a constrained on…
ReText: Text Boosts Generalization in Image-Based Person Re-identification
Timur Mamedov, Karina Kvanchiani, Anton Konushin +1
Generalizable image-based person re-identification (Re-ID) aims to recognize individuals across cameras in unseen domains without retraining. While multiple existing approaches add…
StableTrack: Stabilizing Multi-Object Tracking on Low-Frequency Detections
Matvei Shelukhan, Timur Mamedov, Karina Kvanchiani
Multi-object tracking (MOT) is one of the most challenging tasks in computer vision, where it is important to correctly detect objects and associate these detections across frames.…
Logos as a Well-Tempered Pre-train for Sign Language Recognition
Ilya Ovodov, Petr Surovtsev, Karina Kvanchiani +2
This paper examines two aspects of the isolated sign language recognition (ISLR) task. First, although a certain number of datasets is available, the data for individual sign langu…
HandReader: Advanced Techniques for Efficient Fingerspelling Recognition
Pavel Korotaev, Petr Surovtsev, Alexander Kapitanov +2
Fingerspelling is a significant component of Sign Language (SL), allowing the interpretation of proper names, characterized by fast hand movements during signing. Although previous…