185 citations · 393 across the 41 of their papers we have counts for
14 papers · 1 filter
ThinkBot: Embodied Instruction Following with Thought Chain Reasoning
Guanxing Lu, Ziwei Wang, Changliu Liu +2
Embodied Instruction Following (EIF) requires agents to complete human instruction by interacting objects in complicated surrounding environments. Conventional methods directly con…
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments
Chubin Zhang, Juncheng Yan, Yi Wei +5
Occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing…
Segment and Caption Anything
Xiaoke Huang, Jianfeng Wang, Yansong Tang +5
We propose a method to efficiently equip the Segment Anything Model (SAM) with the ability to generate regional captions. SAM presents strong generalizability to segment anything w…
MCUFormer: Deploying Vision Transformers on Microcontrollers with Limited Memory
Yinan Liang, Ziwei Wang, Xiuwei Xu +3
Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI. Convent…
Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning
Zhiheng Li, Wenjia Geng, Muheng Li +4
In this paper, we propose Skip-Plan, a condensed action space learning method for procedure planning in instructional videos. Current procedure planning methods all stick to the st…
Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer
Guangyi Chen, Xiao Liu, Guangrun Wang +4
Video-language pre-trained models have shown remarkable success in guiding video question-answering (VideoQA) tasks. However, due to the length of video sequences, training large-s…
Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment
Hongbo Liu, Mingda Wu, Kun Yuan +5
Video quality assessment (VQA) has attracted growing attention in recent years. While the great expense of annotating large-scale VQA datasets has become the main obstacle for curr…
Language-free Compositional Action Generation via Decoupling Refinement
Xiao Liu, Guangyi Chen, Yansong Tang +3
Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation. Existing methods largely rely on extensive neural language annotati…
Efficient Text-Guided 3D-Aware Portrait Generation with Score Distillation Sampling on Distribution
Yiji Cheng, Fei Yin, Xiaoke Huang +5
Text-to-3D is an emerging task that allows users to create 3D content with infinite possibilities. Existing works tackle the problem by optimizing a 3D representation with guidance…
SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation
Zhuoyan Luo, Yicheng Xiao, Yong Liu +5
This paper studies referring video object segmentation (RVOS) by boosting video-level visual-linguistic alignment. Recent approaches model the RVOS task as a sequence prediction pr…
Towards Accurate Post-training Quantization for Diffusion Models
Changyuan Wang, Ziwei Wang, Xiuwei Xu +3
In this paper, we propose an accurate data-free post-training quantization framework of diffusion models (ADP-DM) for efficient image generation. Conventional data-free quantizatio…
Efficient Meshy Neural Fields for Animatable Human Avatars
Xiaoke Huang, Yiji Cheng, Yansong Tang +3
Efficiently digitizing high-fidelity animatable human avatars from videos is a challenging and active research topic. Recent volume rendering-based neural representations open a ne…
Semantics-Aware Dynamic Localization and Refinement for Referring Image Segmentation
Zhao Yang, Jiaqi Wang, Yansong Tang +3
Referring image segmentation segments an image from a language expression. With the aim of producing high-quality masks, existing methods often adopt iterative learning approaches…
Global Knowledge Calibration for Fast Open-Vocabulary Segmentation
Kunyang Han, Yong Liu, Jun Hao Liew +8
Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred…