activity
20232025
most citedLaser: Efficient Language-Guided Segmentation in Neural Radiance Fields

7 citations · 8 across the 5 of their papers we have counts for

collaborators

6 papers

cs.CV20257 cited

Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields

Xingyu Miao, Haoran Duan, Yang Bai +5

In this work, we propose a method that leverages CLIP feature distillation, achieving efficient 3D segmentation through language guidance. Unlike previous methods that rely on mult…

cs.CV2024

Relation-Aware Meta-Learning for Zero-shot Sketch-Based Image Retrieval

Yang Liu, Jiale Du, Xinbo Gao +1

Sketch-based image retrieval (SBIR) relies on free-hand sketches to retrieve natural photos within the same class. However, its practical application is limited by its inability to…

cs.CV2024

UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization

Tiantian Geng, Teng Wang, Jinming Duan +4

Video event localization tasks include temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods tend to over-spe…

cs.CV2024

Latent Semantic Consensus For Deterministic Geometric Model Fitting

Guobao Xiao, Jun Yu, Jiayi Ma +2

Estimating reliable geometric model parameters from the data with severe outliers is a fundamental and important task in computer vision. This paper attempts to sample high-quality…

cs.CV2024

Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation

Hao Tang, Ling Shao, Nicu Sebe +1

We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for challenging graph-constrained archi…

cs.CV20231 cited

ECEA: Extensible Co-Existing Attention for Few-Shot Object Detection

Zhimeng Xin, Tianxu Wu, Shiming Chen +3

Few-shot object detection (FSOD) identifies objects from extremely few annotated samples. Most existing FSOD methods, recently, apply the two-stage learning paradigm, which transfe…