Search Results for author:
Found 10 papers, 6 papers with code
Ego-VPA: Egocentric Video Understanding with Parameter-efficient Adaptation
Video understanding typically requires fine-tuning the large backbone when adapting to new domains.
Single-Stage Visual Relationship Learning using Conditional Queries
Research in scene graph generation (SGG) usually considers two-stage models, that is, detecting a set of entities, followed by combining them and labeling all possible relationships.
ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
A new Prompt Tuning for Hierarchical Consistency (ProTeCt) technique is then proposed to calibrate classification across label set granularities.
Class-Incremental Learning with Strong Pre-trained Models
We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations.
Learning of Visual Relations: The Devil is in the Tails
Significant effort has been recently devoted to modeling visual relations.
Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier
Motivated by this, a deep realistic taxonomic classifier (Deep-RTC) is proposed as a new solution to the long-tail problem, combining realism with hierarchical predictions.
Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition
Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task.
Explainable Object-induced Action Decision for Autonomous Vehicles
The new paradigm lies between the end-to-end and pipelined approaches, and is inspired by how humans solve the problem.
Liquid Pouring Monitoring via Rich Sensory Inputs
In the closed-loop system, the ability to monitor the state of the task via rich sensory information is important but often less studied.
Anticipating Daily Intention using On-Wrist Motion Triggered Sensing
The core of the system is a novel Recurrent Neural Network (RNN) and Policy Network (PN), where the RNN encodes visual and motion observation to anticipate intention, and the PN parsimoniously triggers the process of visual observation to reduce computation requirement.
