Search Results for author:
Found 6 papers, 4 papers with code
Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection
We introduce VidTFS, a Training-free, open-vocabulary video goal and action inference framework that combines the frozen vision foundational model (VFM) and large language model (LLM) with a novel dynamic Frame Selection module.
Dissecting Multimodality in VideoQA Transformer Models by Impairing Modality Fusion
Consistent with the findings of QUAG, we find that most of the models achieve near-trivial performance on CLAVI.
PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack
In this work, we introduce a fast, general and accurate adversarial attack that optimises the original non-convex constrained minimisation problem.
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
Adversarial robustness has become a central goal in deep learning, both in the theory and the practice.
Improved Network Robustness with Adversary Critic
Our main idea is: adversarial examples for the robust classifier should be indistinguishable from the regular data of the adversarial target.
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
An adversarial example library for constructing attacks, building defenses, and benchmarking both
