output
20192024
most citedNTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding

1.8k citations

Showing cs.CVShow all

69 papers · 1 filter

cs.CV20236 cited

Continual Referring Expression Comprehension via Dual Modular Memorization

Heng Tao Shen, Cheng Chen, Peng Wang +3

Referring Expression Comprehension (REC) aims to localize an image region of a given object described by a natural-language expression. While promising performance has been demonst…

cs.CV202314 cited

Class Gradient Projection For Continual Learning

Cheng Chen, Ji Zhang, Jingkuan Song +1

Catastrophic forgetting is one of the most critical challenges in Continual Learning (CL). Recent approaches tackle this problem by projecting the gradient update orthogonal to the…

cs.CV20238 cited

Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction

Wanying Zhang, Shen Zhao, Fanyang Meng +2

With potential applications in fields including intelligent surveillance and human-robot interaction, the human motion prediction task has become a hot research topic and also has…

cs.CV20232 cited

P2I-NET: Mapping Camera Pose to Image via Adversarial Learning for New View Synthesis in Real Indoor Environments

Xujie Kang, Kanglin Liu, Jiang Duan +2

Given a new camera pose in an indoor environment, we study the challenging problem of predicting the view from that pose based on a set of reference RGBD views. Existing exp…

cs.CV202318 cited

Fully Transformer-Equipped Architecture for End-to-End Referring Video Object Segmentation

Ping Li, Yu Zhang, Li Yuan +1

Referring Video Object Segmentation (RVOS) requires segmenting the object in video referred by a natural language query. Existing methods mainly rely on sophisticated pipelines to…

cs.CV202330 cited

Efficient Long-Short Temporal Attention Network for Unsupervised Video Object Segmentation

Ping Li, Yu Zhang, Li Yuan +3

Unsupervised Video Object Segmentation (VOS) aims at identifying the contours of primary foreground objects in videos without any prior knowledge. However, previous methods do not…