Vision-language models for vision tasks: A survey
Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks
(DNNs) training, and they usually train a DNN for each single visual recognition task …
(DNNs) training, and they usually train a DNN for each single visual recognition task …
Vision language models in autonomous driving and intelligent transportation systems
The applications of Vision-Language Models (VLMs) in the fields of Autonomous Driving
(AD) and Intelligent Transportation Systems (ITS) have attracted widespread attention due to …
(AD) and Intelligent Transportation Systems (ITS) have attracted widespread attention due to …
Unipt: Universal parallel tuning for transfer learning with efficient parameter and memory
Parameter-efficient transfer learning (PETL) ie fine-tuning a small portion of parameters is an
effective strategy for adapting pre-trained models to downstream domains. To further reduce …
effective strategy for adapting pre-trained models to downstream domains. To further reduce …
From static to dynamic: Adapting landmark-aware image models for facial expression recognition in videos
Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations,
eg, insufficient quantity and diversity of pose, occlusion and illumination, as well as the …
eg, insufficient quantity and diversity of pose, occlusion and illumination, as well as the …
Vision language models in autonomous driving: A survey and outlook
The applications of Vision-Language Models (VLMs) in the field of Autonomous Driving (AD)
have attracted widespread attention due to their outstanding performance and the ability to …
have attracted widespread attention due to their outstanding performance and the ability to …
Listen as you wish: Fusion of audio and text for cross-modal event detection in smart cities
In the era of smart cities, the advent of the Internet of Things technology has catalyzed the
proliferation of multimodal sensor data, presenting new challenges in cross-modal event …
proliferation of multimodal sensor data, presenting new challenges in cross-modal event …
GPT-4V as Traffic Assistant: An In-depth Look at Vision Language Model on Complex Traffic Events
The recognition and understanding of traffic incidents, particularly traffic accidents, is a topic
of paramount importance in the realm of intelligent transportation systems and intelligent …
of paramount importance in the realm of intelligent transportation systems and intelligent …
CFMMC-Align: Coarse-Fine Multi-Modal Contrastive Alignment Network for Traffic Event Video Question Answering
Traffic video question answering (TrafficVQA) constitutes a specialized VideoQA task
designed to enhance the basic comprehension and intricate reasoning capacities of videos …
designed to enhance the basic comprehension and intricate reasoning capacities of videos …
Video-Language Alignment Pre-training via Spatio-Temporal Graph Transformer
SX Zhang, H Wang, X Zhu, W Gu, T Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Video-language alignment is a crucial multi-modal task that benefits various downstream
applications, eg, video-text retrieval and video question answering. Existing methods either …
applications, eg, video-text retrieval and video question answering. Existing methods either …
Foundation Models for Video Understanding: A Survey
Video Foundation Models (ViFMs) aim to learn a general-purpose representation for various
video understanding tasks. Leveraging large-scale datasets and powerful models, ViFMs …
video understanding tasks. Leveraging large-scale datasets and powerful models, ViFMs …