12 citations · 25 across the 27 of their papers we have counts for
23 papers · 1 filter
BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance Grounding
Yijie Su, Yakun Zhu, Yi Bin +5
Language-guided 3D affordance grounding aims to localize functional regions on 3D objects according to interaction intents. However, existing methods exhibit poor generalization to…
GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning
Yakun Zhu, Yi Bin, Yujuan Ding +5
Despite progress in vision-language models, 3D spatial reasoning from 2D images remains challenging. Text-based methods describe intermediate geometry with discrete tokens, limitin…
Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning
Cheng Chen, Pengpeng Zeng, Yuyu Guo +3
Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors ( and ), creating a composite update to t…
Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learning
Yihang Duan, Jiong Wang, Pengpeng Zeng +5
The goal of Open-Vocabulary Compositional Zero-Shot Learning (OV-CZSL) is to recognize attribute-object compositions in the open-vocabulary setting, where compositions of both seen…
TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelity
Xiao Cai, Pengpeng Zeng, Ji Zhang +3
Precise spatial fidelity in Image-to-3D multi-instance generation is critical for downstream real-world applications. Recent work attempts to address this by fine-tuning pre-traine…
From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
Cheng Chen, Yuyu Guo, Pengpeng Zeng +4
Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder to the input of the…
Reversible Inversion for Training-Free Exemplar-guided Image Editing
Yuke Li, Lianli Gao, Ji Zhang +5
Exemplar-guided Image Editing (EIE) aims to modify a source image according to a visual reference. Existing approaches often require large-scale pre-training to learn relationships…
HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models
Haoxi Zeng, Haoxuan Li, Yi Bin +4
Contrastive Language-Image Pre-training (CLIP) has demonstrated remarkable generalization ability and strong performance across a wide range of vision-language tasks. However, due…
A Survey on Efficient Vision-Language-Action Models
Zhaoshu Yu, Bo Wang, Pengpeng Zeng +7
Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction. Despite their re…
Towards Generalized and Training-Free Text-Guided Semantic Manipulation
Yu Hong, Xiao Cai, Pengpeng Zeng +4
Text-guided semantic manipulation refers to semantically editing an image generated from a source prompt to match a target prompt, enabling the desired semantic changes (e.g., addi…
CFReID: Continual Few-shot Person Re-Identification
Hao Ni, Lianli Gao, Pengpeng Zeng +2
Real-world surveillance systems are dynamically evolving, requiring a person Re-identification model to continuously handle newly incoming data from various domains. To cope with t…
Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
Shihan Wu, Ji Zhang, Pengpeng Zeng +3
Prompt tuning (PT) has long been recognized as an effective and efficient paradigm for transferring large pre-trained vision-language models (VLMs) to downstream tasks by learning…
GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark
Xiao Cai, Sitong Su, Jingkuan Song +6
Text-to-3D (T23D) generation has emerged as a crucial visual generation task, aiming at synthesizing 3D content from textual descriptions. Studies of this task are currently shifti…
SeMv-3D: Towards Concurrency of Semantic and Multi-view Consistency in General Text-to-3D Generation
Xiao Cai, Pengpeng Zeng, Lianli Gao +3
General Text-to-3D (GT23D) generation is crucial for creating diverse 3D content across objects and scenes, yet it faces two key challenges: 1) ensuring semantic consistency betwee…
Text-Video Retrieval with Global-Local Semantic Consistent Learning
Haonan Zhang, Pengpeng Zeng, Lianli Gao +4
Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involv…
ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval
Kaipeng Fang, Jingkuan Song, Lianli Gao +4
The goal of Universal Cross-Domain Retrieval (UCDR) is to achieve robust performance in generalized test scenarios, wherein data may belong to strictly unknown domains and categori…
Generalized Unbiased Scene Graph Generation
Xinyu Lyu, Lianli Gao, Junlin Xie +4
Existing Unbiased Scene Graph Generation (USGG) methods only focus on addressing the predicate-level imbalance that high-frequency classes dominate predictions of rare ones, while…
Visual Commonsense-aware Representation Network for Video Captioning
Pengpeng Zeng, Haonan Zhang, Lianli Gao +3
Generating consecutive descriptions for videos, i.e., Video Captioning, requires taking full advantage of visual representation along with the generation process. Existing video ca…
Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generation
Chaofan Zheng, Lianli Gao, Xinyu Lyu +3
The current studies of Scene Graph Generation (SGG) focus on solving the long-tailed problem for generating unbiased scene graphs. However, most de-biasing methods overemphasize th…
Adaptive Fine-Grained Predicates Learning for Scene Graph Generation
Xinyu Lyu, Lianli Gao, Pengpeng Zeng +2
The performance of current Scene Graph Generation (SGG) models is severely hampered by hard-to-distinguish predicates, e.g., woman-on/standing on/walking on-beach. As general SGG m…
From Pixels to Objects: Cubic Visual Attention for Visual Question Answering
Jingkuan Song, Pengpeng Zeng, Lianli Gao +1
Recently, attention-based Visual Question Answering (VQA) has achieved great success by utilizing question to selectively target different visual areas that are related to the answ…
Structured Two-stream Attention Network for Video Question Answering
Lianli Gao, Pengpeng Zeng, Jingkuan Song +4
To date, visual question answering (VQA) (i.e., image QA and video QA) is still a holy grail in vision and language understanding, especially for video QA. Compared with image QA t…
Support-set based Multi-modal Representation Enhancement for Video Captioning
Xiaoya Chen, Jingkuan Song, Pengpeng Zeng +2
Video captioning is a challenging task that necessitates a thorough comprehension of visual scenes. Existing methods follow a typical one-to-one mapping, which concentrates on a li…