Search Results for author:
Found 10 papers, 2 papers with code
Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models
Zero-Shot Anomaly Detection (ZSAD) is an emerging AD paradigm.
ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos
To address this, we propose a simple fine-tuning technique, Action Concept Enhancement (ACE), to improve the robustness and concept understanding of VLMs in procedural action classification.
Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos
We present a novel method for weakly-supervised action segmentation and unseen error detection in anomalous instructional videos.
DRAMA: Joint Risk Localization and Captioning in Driving
We make this data available to the community for further research.
Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos
Experimental results show efficacy of the proposed methods both qualitatively and quantitatively in two domains of cooking and assembly.
SSP: Single Shot Future Trajectory Prediction
Third, the semantic context of the scene are modeled and take into account the environmental constraints that potentially influence the future motion.
NEMO: Future Object Localization Using Noisy Ego Priors
In the proposed approach, a predictive distribution of future forecast is jointly modeled with the uncertainty of predictions.
Dynamic Traffic Scene Classification with Space-Time Coherence
This paper examines the problem of dynamic traffic scene classification under space-time variations in viewpoint that arise from video captured on-board a moving vehicle.
High Quality Prediction of Protein Q8 Secondary Structure by Diverse Neural Network Architectures
In the spirit of reproducible research we make our data, models and code available, aiming to set a gold standard for purity of training and testing sets.
SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks
We propose SketchParse, the first deep-network architecture for fully automatic parsing of freehand object sketches.
