44 citations · 59 across the 6 of their papers we have counts for
8 papers
Video Timeline Modeling For News Story Understanding
Meng Liu, Mingda Zhang, Jialu Liu +5
In this paper, we present a novel problem, namely video timeline modeling. Our objective is to create a video-associated timeline from a set of videos related to a specific topic,…
VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
Zihao Zhu, Mingda Zhang, Shaokui Wei +2
The role of data in building AI systems has recently been emphasized by the emerging concept of data-centric AI. Unfortunately, in the real-world, datasets may contain dirty sample…
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
Shaokui Wei, Mingda Zhang, Hongyuan Zha +1
Backdoor attacks are serious security threats to machine learning models where an adversary can inject poisoned samples into the training set, causing a backdoored model which pred…
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Zihao Zhu, Mingda Zhang, Shaokui Wei +3
Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing at…
Cap2Det: Learning to Amplify Weak Caption Supervision for Object Detection
Keren Ye, Mingda Zhang, Adriana Kovashka +3
Learning to localize and name object instances is a fundamental problem in vision, but state-of-the-art approaches rely on expensive bounding box supervision. While weakly supervis…
Learning to discover and localize visual objects with open vocabulary
Keren Ye, Mingda Zhang, Wei Li +3
To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techn…