Search Results for author:
Found 20 papers, 12 papers with code
Window Token Concatenation for Efficient Visual Large Language Models
To further enhance the performance on fine-grained visual understanding tasks, we introduce WiCo+, which decomposes the visual tokens in later layers of the LLM.
Visual Large Language Models for Generalized and Specialized Applications
Visual-language models (VLM) have emerged as a powerful tool for learning a unified embedding space for vision and language.
Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
Existing approaches focus on the closed-set setting where an action detector is trained and tested on videos from a fixed set of action categories.
Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment
Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos.
Facial Affective Behavior Analysis with Instruction Tuning
Our initiative on the dataset and benchmarks reveal the nature and rationale of facial affective behaviors, i. e., fine-grained facial movement, interpretability, and reasoning.
Latent Space Energy-based Model for Fine-grained Open Set Recognition
A recent trend in OSR shows the benefit of generative models to discriminative unknown detection.
On Model Explanations with Transferable Neural Pathways
Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model.
Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting
In this paper, we set up an egocentric 3D hand trajectory forecasting task that aims to predict hand trajectories in a 3D space from early observed RGB videos in a first-person view.
Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
Compositional zero-shot learning (CZSL) task aims to recognize unseen compositional visual concepts, e. g., sliced tomatoes, where the model is learned only from the seen compositions, e. g., sliced potatoes and red tomatoes.
3D-Aware Facial Landmark Detection via Multi-View Consistent Training on Synthetic Data
Accurate facial landmark detection on wild images plays an essential role in human-computer interaction, entertainment, and medical applications.
Towards Open Set Video Anomaly Detection
We develop a novel weakly supervised method for the OpenVAD problem by integrating evidential deep learning (EDL) and normalizing flows (NFs) into a multiple instance learning (MIL) framework.
OpenTAL: Towards Open Set Temporal Action Localization
The OpenTAL is general to enable existing TAL models for open set scenarios, and experimental results on THUMOS14 and ActivityNet1. 3 benchmarks show the effectiveness of our method.
Gradient Frequency Modulation for Visually Explaining Video Understanding Models
In many applications, it is essential to understand why a machine learning model makes the decisions it does, but this is inhibited by the black-box nature of state-of-the-art neural networks.
Evidential Deep Learning for Open Set Action Recognition
Different from image data, video actions are more challenging to be recognized in an open-set setting due to the uncertain temporal dynamics and static bias of human actions.
DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation
Traffic accident anticipation aims to accurately and promptly predict the occurrence of a future accident from dashcam videos, which is vital for a safety-guaranteed self-driving system.
Group Activity Prediction with Sequential Relational Anticipation Model
Our model explicitly anticipates both activity features and positions by two graph auto-encoders, aiming to learn a discriminative group representation for group activity prediction.
Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning
The derived uncertainty-based ranking loss is found to significantly boost model performance by improving the quality of relational features.
Ranked #2 on
Accident Anticipation
on CCD
Object-Aware Centroid Voting for Monocular 3D Object Detection
Monocular 3D object detection aims to detect objects in a 3D physical world from a single camera.
