检索结果-内蒙古大学图书馆

Deepfake Network Architecture Attribution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Tianyun Huang, Ziyao Cao, Juan Li, Lei Li, Xirong Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adversarial Network (GAN) models and obtain high accuracies. While encouraging, these works are restricted to model-level attribution, only capable of handling images generated by seen models with a specific seed, loss and dataset, which is limited in real-world scenarios when fake images may be generated by privately trained models. This motivates us to ask whether it is possible to attribute fake images to the source models’ architectures even if they are finetuned or retrained under different configurations. In this work, we present the first study on Deepfake Network Architecture Attribution to attribute fake images on architecture-level. Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, we provide a simple yet effective solution named DNA-Det for this problem. Extensive experiments on multiple cross-test setups and a large-scale dataset demonstrate the effectiveness of DNA-Det. Our source code and dataset can be found here: https://***/ICTMCG/DNA-Det Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

学校读者我要写书评

暂无评论

Hand and gesture

Virtual Reality & intelligent Hardware 2021年第3期3卷 I0001-I0002页

作者： Xilin CHEN Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China

Hands play an important role in our daily *** use our hands for manipulation in working,emphasis in speaking,communication in non-verbal environment,*** gesture not only uses for simple commands in traffic control,but also extends as a kind of language-sign *** the areas of VR/AR and HCI,understanding hand and its action can greatly improve user *** covers a broad topics related to hands,including hand detection,tracking,hand pose estimation,gesture recognition,and sign language *** papers are collected in this *** cover different topics related to hand and gesture.

关键词： verbal language. hands

HUMAN SIMULACRA: BENCHMARKING THE PERSONIFICATION OF LARGE LANGUAGE MODELS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Qiujie Feng, Qiming Zhang, Tianqi Li, Qingqiu Yang, Linyi Zhang, Yuejie Feng, Rui He, Liang Gao, Shang Zhang, Yue School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Tongji University China University College London United Kingdom Huawei Noah’s Ark Lab Canada Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention China Deakin University Australia Westlake University China Westlake Institute for Advanced Study China

Large Language Models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted the attention of the social science community, who see the potential in leveraging LLMs to replace human participants in experiments, thereby reducing research costs and complexity. In this paper, we introduce a benchmark for LLMs personification, including a strategy for constructing virtual characters’ life stories from the ground up, a Multi-Agent Cognitive Mechanism capable of simulating human cognitive processes, and a psychology-guided evaluation method to assess human simulations from both self and observational perspectives. Experimental results demonstrate that our constructed simulacra can produce personified responses that align with their target characters. We hope this work will serve as a benchmark in the field of human simulation, paving the way for future research. © 2024, CC BY-NC-SA.

关键词： Digital elevation model

SASA-Net: A spatial-aware self-attention mechanism for building protein 3D structure directly from inter-residue distances

学校读者我要写书评

暂无评论

SASA-Net: A spatial-aware self-attention mechanism for build...

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Gong, Tiansu Ju, Fusong Sun, Shiwei Bu, Dongbo Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Zhongke Big Data Academy Henan Zhengzhou450046 China

ISBN: (纸本)9781665401265

Protein structure prediction has achieved considerable progresses mainly due to the increased accuracy of inter-residue distance estimation and the application of deep learning *** of the distance-based ab initio prediction approaches adopt a two-step diagram: constructing a potential function based on the estimated inter-residue distances, and then build a 3D structure that minimizes the potential function. These approaches have proven very promising;however, they still suffer from several limitations, especially the inaccuracies incurred by the handcrafted potential ***, we present SASA-Net, a deep learning-based approach that directly learns protein 3D structure from the estimated inter-residue distances. Unlike the existing approach simply representing protein structures as coordinates of atoms, SASA-Net represents protein structures using pose of residues, i.e., the coordinate system of each individual residue in which all backbone atoms of this residue are fixed. The key element of SASA-Net is a spatial-aware self-attention mechanism, which is able to adjust a residue's pose according to all other residues' features and the estimated distances between residues. By iteratively applying the spatial-aware self-attention mechanism, SASA-Net continuously improves the structure and finally acquires a structure with high accuracy. Using the CATH35 proteins as representatives, we demonstrate that SASA-Net is able to accurately and efficiently build structures from the estimated inter-residue distances. The high accuracy and efficiency of SASA-Net enables an end-to-end neural network model for protein structure prediction through combining SASA-Net and an neural network for inter-residue distance prediction. Source code of SASA-Net is available at https://*** gongtiansu/SASA-Net/ © 2021 IEEE.

关键词： Proteins

Spatiotemporal Activity Modeling via Hierarchical Cross-Modal Embedding : Extended Abstract

学校读者我要写书评

暂无评论

Spatiotemporal Activity Modeling via Hierarchical Cross-Moda...

International Conference on Data Engineering

作者： Yang Liu Xiang Ao Linfeng Dong Chao Zhang Jin Wang Qing He Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Zhejiang University Hangzhou China College of Computing Georgia Tech United States Megagon Labs Mountain View United States

With the ever-increasing urbanization process, modeling people’s spatiotemporal activities from their online traces has become a crucial task. State-of-the-art methods for this task rely on cross-modal embedding, which maps items from different modalities (e.g., location, time, text) into the same latent space. Despite their inspiring results, existing cross-modal embedding methods merely capture co-occurrences between items without modeling their high-order interactions. In this paper, we first construct the user interaction graph and the activity graph from raw data records and propose a hierarchical cross-modal embedding method that takes the high-order relationships into consideration. We introduce both inter-record and intra-record meta-graph structures, which enable learning distributed representations that preserve high-order proximities across graphs from different layers. Our empirical experiments on three real-world datasets demonstrate that our method not only outperforms state-of-the-art methods for spatiotemporal activity prediction but also captures cross-modal proximity at a finer granularity.

关键词：

Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huang, Bingchen Chen, Zhineng Zhou, Peng Chen, Jiayin Wu, Zuxuan Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China University of Maryland College ParkMD United States

The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the discrepancy between classes of different tasks is not well learned (i.e., inter-task confusion, ITC), and certain priority is still given to the latest class batch (i.e., old-new confusion, ONC). We empirically validate the side effects of the two types of confusion. Meanwhile, a novel solution called Task Correlated Incremental Learning (TCIL) is proposed to encourage discriminative and fair feature utilization across tasks. TCIL performs a multi-level knowledge distillation to propagate knowledge learned from old tasks to the new one. It establishes information flow paths at both feature and logit levels, enabling the learning to be aware of old classes. Besides, attention mechanism and classifier re-scoring are applied to generate more fair classification scores. We conduct extensive experiments on CIFAR100 and ImageNet100 datasets. The results demonstrate that TCIL consistently achieves state-of-the-art accuracy. It mitigates both ITC and ONC, while showing advantages in battle with catastrophic forgetting even no rehearsal memory is reserved. 1 Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

Knowledge Graph Embedding Based Graph Convolutional Network for Link Prediction

学校读者我要写书评

暂无评论

Knowledge Graph Embedding Based Graph Convolutional Network ...

International Conference on Advanced Cloud and Big Data (CBD)

作者： Qiang Wu Qing He Henan Institute of Advanced Technology Zhengzhou University Zhengzhou P.R. China Key Lab of Intelligent Information Processing of Chinese Academy of Science (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Science Beijing China

Knowledge Graph Embedding (KGE) aims to capture the inherent structural information within knowledge graphs (KGs) by means of representation learning. This is of paramount importance for various downstream tasks, including personalized recommendations, intelligent search, and relation extraction. Graph Convolutional Networks (GCNs), a type of neural network, have recently demonstrated significant success in modeling data structured as graphs. However, these models often overlook the intricate interrelation information between neighboring nodes, which can offer valuable insights for enhancing node embeddings. In this article, we present a knowledge graph embedding based graph convolutional network for link prediction. First, we utilize embeddings to represent entities and relations. Second, we perform circular correlation on subject embedding and relation embedding to generate two matrix and achieve full fusion of embedding at the element level. Third, we generate self-attention vectors using one of the matrices and perform the Hadamard product with the other matrix. Thereafter, new node features are generated through graph convolutional networks and residual unit. Finally, we use the scoring function to score the candidate triples. The experimental results demonstrate that our model achieves improved performance compared with a wide variety of baseline models.

关键词：

ObjectFormer for Image Manipulation Detection and Localization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Junke Wu, Zuxuan Chen, Jingjing Han, Xintong Shrivastava, Abhinav Lim, Ser-Nam Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Huya Inc University of Maryland United States Meta AI

Recent advances in image editing techniques have posed serious challenges to the trustworthiness of multimedia data, which drives the research of image tampering detection. In this paper, we propose ObjectFormer to detect and localize image manipulations. To capture subtle manipulation traces that are no longer visible in the RGB domain, we extract high-frequency features of the images and combine them with RGB features as multimodal patch embeddings. Additionally, we use a set of learnable object prototypes as mid-level representations to model the object-level consistencies among different regions, which are further used to refine patch embeddings to capture the patch-level consistencies. We conduct extensive experiments on various datasets and the results verify the effectiveness of the proposed method, outperforming state-of-the-art tampering detection and localization methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

DFTR: Depth-supervised Fusion Transformer for Salient Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Heqin Sun, Xu Li, Yuexiang Ma, Kai Zhou, S. Kevin Zheng, Yefeng Key Lab of Intelligent Information Processing Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China Tencent Jarvis Lab Shenzhen China University of Science and Technology of China Suzhou215123 China

Automated salient object detection (SOD) plays an increasingly crucial role in many computer vision applications. By reformulating the depth information as supervision rather than as input, depth-supervised convolutional neural networks (CNN) have achieved promising results on both RGB and RGB-D SOD scenarios with the merits of no requirements for extra depth networks and depth inputs in the inference stage. This paper, for the first time, seeks to expand the applicability of depth supervision to the Transformer architecture. Specifically, we develop a Depth-supervised Fusion TRansformer (DFTR), to further improve the accuracy of both RGB and RGB-D SOD. The proposed DFTR involves three primary features: 1) DFTR, to the best of our knowledge, is the first pure Transformer-based model for depth-supervised SOD;2) A multi-scale feature aggregation (MFA) module is proposed to fully exploit the multi-scale features encoded by the Swin Transformer in a coarse-to-fine manner;3) To enable bidirectional information flow across different streams of features, a novel multi-stage feature fusion (MFF) module is further integrated into our DFTR with the emphasis on salient regions at different network learning stages. We extensively evaluate the proposed DFTR on ten benchmarking datasets. Experimental results show that our DFTR consistently outperforms the existing state-of-the-art methods for both RGB and RGB-D SOD tasks. The code and model will be made publicly available. © 2022, CC BY-NC-SA.

关键词： Object detection