https://github.com/roberto1648/adversarial-perturbations-on-images-and-videos
공식 코드Targeted Nonlinear Adversarial Perturbations in Images and Videos
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Action Localization is finding the spatial and temporal co ordinates for an action in a video. An action localization model will identify which frame an action start and ends in video and return the x,y coordinates of an action. Further the co ordinates will change when the object performing action undergoes a displacement.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Targeted Nonlinear Adversarial Perturbations in Images and Videos
Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction
MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning
LoRD: Adapting Differentiable Driving Policies to Distribution Shifts
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interaction
Sequential modeling of Sessions using Recurrent Neural Networks for Skip Prediction
PhysORD: A Neuro-Symbolic Approach for Physics-infused Motion Prediction in Off-road Driving
HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization
On Mechanistic Knowledge Localization in Text-to-Image Generative Models
Towards Explainable Motion Prediction using Heterogeneous Graph Representations
Towards Effective Image Manipulation Detection with Proposal Contrastive Learning
A Neuro-Symbolic Approach for Enhanced Human Motion Prediction
Few-Shot Temporal Action Localization with Query Adaptive Transformer
Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
Rebuilding ROME : Resolving Model Collapse during Sequential Model Editing
Exploring Navigation Maps for Learning-Based Motion Prediction
ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.