1

DeCo : Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-to-Fine Contrastive Ranking
Understanding dense action in videos is a fundamental challenge towards the generalization of vision models. Several works show that …
PDF 引用
DeCo : Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-to-Fine Contrastive Ranking
FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotations
引用
Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction
The Multiplane Image (MPI), containing a set of fronto-parallel RGBA layers, is an effective and efficient representation for view …
PDF 引用
Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction
Technical Report for EgoTracks in Ego4D Challenge 2023
引用
Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training
The task of weakly supervised temporal sentence grounding aims at finding the corresponding temporal moments of a language description …
PDF 引用
Weakly Supervised Temporal Sentence Grounding With Uncertainty-Guided Self-Training
Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos
Object affordance is an important concept in hand-object interaction, providing information on action possibilities based on human …
PDF 引用
Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos
Learning Video-independent Eye Contact Segmentation from In-the-Wild Videos
Human eye contact is a form of non-verbal communication and can have a great influence on social behavior. Since the location and size …
PDF 引用 コード
Learning Video-independent Eye Contact Segmentation from In-the-Wild Videos
Background Mixup Data Augmentation for Hand and Object-in-Contact Detection
Detecting the positions of human hands and objects-in-contact (hand-object detection) in each video frame is vital for understanding …
PDF 引用
Background Mixup Data Augmentation for Hand and Object-in-Contact Detection
CompNVS: Novel View Synthesis with Scene Completion
We introduce a scalable framework for novel view synthesis (NVS) from RGB-D images with largely incomplete scene coverage. While …
PDF 引用 DOI
CompNVS: Novel View Synthesis with Scene Completion
Compound Prototype Matching for Few-shot Action Recognition
Few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. In this work, …
PDF 引用 DOI
Compound Prototype Matching for Few-shot Action Recognition