6 accepted papers
Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens or hundreds of tokens, the limited context length of large language models (LLMs) forces the VLMs to perceive the frames…
Understanding scenes in movies is crucial for a variety of applications such as video moderation, search, and recommendation. However, labeling individual scenes is a time-consuming process. In contrast, movie level metadata (e.g., genre, synopsis, etc.) regularly gets produced as part of the film p…
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To address this challenge, we introduce a novel training framew…
Scenes play a crucial role in breaking the storyline of movies and TV episodes into semantically cohesive parts. However, given their complex temporal structure, finding scene boundaries can be a challenging task requiring large amounts of labeled training data. To address this challenge, we present…
In transfer learning, one seeks to transfer related information from source tasks with sufficient data to help with the learning of target task with only limited data. In this paper, we propose a novel Coupled End-to-end Transfer Learning (CETL) framework, which mainly consists of two convolutional…
Human age is considered an important biometric trait for human identification or search. Recent research shows that the aging features deeply learned from large-scale data lead to significant performance improvement on facial image-based age estimation. However, age-related ordinal information is to…