18 citations · 139 across the 44 of their papers we have counts for
44 papers
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…
Any Target Can be Offense: Adversarial Example Generation via Generalized Latent Infection
Youheng Sun, Shengming Yuan, Xuanhan Wang +2
Targeted adversarial attack, which aims to mislead a model to recognize any image as a target object by imperceptible perturbations, has become a mainstream tool for vulnerability…
Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
Xinyu Lyu, Beitao Chen, Lianli Gao +2
Although Large Visual Language Models (LVLMs) have demonstrated exceptional abilities in understanding multimodal data, they invariably suffer from hallucinations, leading to a dis…
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…
RoScenes: A Large-scale Multi-view 3D Dataset for Roadside Perception
Xiaosu Zhu, Hualian Sheng, Sijia Cai +7
We introduce RoScenes, the largest multi-view roadside perception dataset, which aims to shed light on the development of vision-centric Bird's Eye View (BEV) approaches for more c…
AICL: Action In-Context Learning for Video Diffusion Model
Jianzhi Liu, Junchen Zhu, Lianli Gao +2
The open-domain video generation models are constrained by the scale of the training video datasets, and some less common actions still cannot be generated. Some researchers explor…
CoIN: A Benchmark of Continual Instruction tuNing for Multimodel Large Language Model
Cheng Chen, Junchen Zhu, Xu Luo +3
Instruction tuning represents a prevalent strategy employed by Multimodal Large Language Models (MLLMs) to align with human instructions and adapt to new tasks. Nevertheless, MLLMs…
Training-Free Semantic Video Composition via Pre-trained Diffusion Model
Jiaqi Guo, Sitong Su, Junchen Zhu +2
The video composition task aims to integrate specified foregrounds and backgrounds from different videos into a harmonious composite. Current approaches, predominantly trained on v…
Towards Redundancy-Free Sub-networks in Continual Learning
Cheng Chen, Jingkuan Song, LianLi Gao +1
Catastrophic Forgetting (CF) is a prominent issue in continual learning. Parameter isolation addresses this challenge by masking a sub-network for each task to mitigate interferenc…
Make-A-Storyboard: A General Framework for Storyboard with Disentangled and Merged Control
Sitong Su, Litao Guo, Lianli Gao +2
Story Visualization aims to generate images aligned with story prompts, reflecting the coherence of storybooks through visual consistency among characters and scenes.Whereas curren…
F3-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis
Sitong Su, Jianzhi Liu, Lianli Gao +1
Recently Text-to-Video (T2V) synthesis has undergone a breakthrough by training transformers or diffusion models on large-scale datasets. Nevertheless, inferring such large models…
ALF: Adaptive Label Finetuning for Scene Graph Generation
Qishen Chen, Jianzhi Liu, Xinyu Lyu +3
Scene Graph Generation (SGG) endeavors to predict the relationships between subjects and objects in a given image. Nevertheless, the long-tail distribution of relations often leads…
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…
Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection
Tao He, Lianli Gao, Jingkuan Song +1
Scene graph generation (SGG) and human-object interaction (HOI) detection are two important visual tasks aiming at localising and recognising relationships between objects, and int…
From Channel Bias to Feature Redundancy: Uncovering the "Less is More" Principle in Few-Shot Learning
Ji Zhang, Xu Luo, Lianli Gao +3
Deep neural networks often fail to adapt representations to novel tasks under distribution shifts, especially when only a few examples are available. This paper identifies a core o…
Local-Global Information Interaction Debiasing for Dynamic Scene Graph Generation
Xinyu Lyu, Jingwei Liu, Yuyu Guo +1
The task of dynamic scene graph generation (DynSGG) aims to generate scene graphs for given videos, which involves modeling the spatial-temporal information in the video. However,…
Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval
Hao Li, Jingkuan Song, Lianli Gao +2
Cross-modal Retrieval methods build similarity relations between vision and language modalities by jointly learning a common representation space. However, the predictions are ofte…
DePT: Decoupled Prompt Tuning
Ji Zhang, Shihan Wu, Lianli Gao +2
This work breaks through the Base-New Tradeoff (BNT)dilemma in prompt tuning, i.e., the better the tuned model generalizes to the base (or target) task, the worse it generalizes to…
CIParsing: Unifying Causality Properties into Multiple Human Parsing
Xiaojia Chen, Xuanhan Wang, Lianli Gao +3
Existing methods of multiple human parsing (MHP) apply statistical models to acquire underlying associations between images and labeled body parts. However, acquired associations o…
From Global to Local: Multi-scale Out-of-distribution Detection
Ji Zhang, Lianli Gao, Bingguang Hao +3
Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representatio…
Informative Scene Graph Generation via Debiasing
Lianli Gao, Xinyu Lyu, Yuyu Guo +5
Scene graph generation aims to detect visual relationship triplets, (subject, predicate, object). Due to biases in data, current models tend to predict common predicates, e.g. "on"…
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…
MobileVidFactory: Automatic Diffusion-Based Social Media Video Generation for Mobile Devices from Text
Junchen Zhu, Huan Yang, Wenjing Wang +8
Videos for mobile devices become the most popular access to share and acquire information recently. For the convenience of users' creation, in this paper, we present a system, name…
Prototype-based Embedding Network for Scene Graph Generation
Chaofan Zheng, Xinyu Lyu, Lianli Gao +2
Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs. However, due to the diverse visual appearance of numerous p…