25 Hits in 5.9 sec

Dataset of Fake News Detection and Fact Verification: A Survey [article]

Taichi Murayama
2021 arXiv   pre-print
We surveyed 118 datasets related to fake news research on a large scale from three perspectives: (1) fake news detection, (2) fact verification, and (3) other tasks; for example, the analysis of fake news  ...  The resources for these studies are mainly available as public datasets taken from Web data.  ...  It is annotated using six fine-grained labels (true, mostly true, half true, mostly false, false, and pants on fire) and comprises 12,836 short statement claims from 2007 to 2016 along with information  ... 
arXiv:2111.03299v1 fatcat:noyhfssx7fe6rhsndcjosbi7oi

Multi-Expert Human Action Recognition with Hierarchical Super-Class Learning [article]

Hojat Asgarian Dehkordi, Ali Soltani Nezhad, Hossein Kashiani, Shahriar Baradaran Shokouhi, Ahmad Ayatollahi
2021 arXiv   pre-print
In the proposed approach, a coarse-grained phase selects the most relevant fine-grained experts.  ...  Extensive experimental evaluations are conducted on various public human action recognition datasets, including Stanford40, Pascal VOC 2012 Action, BU101+, and IHAR datasets.  ...  Finally, FGC determines human action recognition classes. 3.1. Fine-grained Phase Figure 2 (a) depicts the entire architecture of FGC in the fine-grained clas- sification phase.  ... 
arXiv:2112.07015v1 fatcat:goyyprh6ibbn3iskpnw7nllyqi

Methods for Efficiently Constructing Text-dialogue-agent System using Existing Anime Characters

Ryo Ishii, Ryuichiro Higashinaka, Koh Mitsuda, Taichi Katayama, Masahiro Mizukami, Junji Tomita, Hidetoshi Kawabata, Emi Yamaguchi, Noritake Adachi, Yushi Aono
2021 Journal of Information Processing  
We also propose a new utterance generation method that uses a neural translation model with the collected data.  ...  We created a text-dialogue agent system of a popular existing anime character using our proposed generation methods.  ...  Although certain aspects of personality can be converted on the basis of the Big-5, such dimensions are too broad and rough when agents need to generate fine-grained answers related to their personality  ... 
doi:10.2197/ipsjjip.29.30 fatcat:nphvvtz7uzh5zmm7pnw33wtqnq

A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos [article]

Frank F. Xu, Lei Ji, Botian Shi, Junyi Du, Graham Neubig, Yonatan Bisk, Nan Duan
2020 arXiv   pre-print
to predict every action of a procedure in a structured form.  ...  However, it provides only an indirect, overall evaluation of multimodal models with no finer-grained quantitative measure of what they have learned.  ...  However, this dataset does not contain more fine-grained annotations in a structured form. • HowTo100M 10 (Miech et al., 2019).  ... 
arXiv:2005.00706v2 fatcat:udatzb5i35e5voc2dtub44zoli

Motion-aware Contrastive Video Representation Learning via Foreground-background Merging [article]

Shuangrui Ding, Maomao Li, Tianyu Yang, Rui Qian, Haohang Xu, Qingyi Chen, Jue Wang, Hongkai Xiong
2022 arXiv   pre-print
Such bias makes the model suffer from weak generalization ability, leading to worse performance on downstream tasks such as action recognition.  ...  When naively pulling two augmented views of a video closer, the model however tends to learn the common static background as a shortcut but fails to capture the motion information, a phenomenon dubbed  ...  Besides common action recognition benchmarks, we finetune and test our FAME on a more challenging fine-grained dataset Diving48 and report the results in Table 2 .  ... 
arXiv:2109.15130v3 fatcat:qy2voj5fxfbl3dla7svjpp54l4

Large-Scale Automatic Labeling of Video Events with Verbs Based on Event-Participant Interaction [article]

Andrei Barbu, Alexander Bridge, Dan Coroian, Sven Dickinson, Sam Mussman, Siddharth Narayanaswamy, Dhaval Salvi, Lara Schmidt, Jiangnan Shangguan, Jeffrey Mark Siskind, Jarrell Waggoner, Song Wang (+2 others)
2012 arXiv   pre-print
away all object-class information and fine-grained image characteristics, and relying solely on the coarse-grained motion of the event participants.  ...  This indicates that successful event recognition depends more on the choice of appropriate features that characterize the linguistic invariants of the event classes than on the particular classifier algorithms  ...  The event classes side and jack in the WEIZMANN dataset, the event classes Swing-Bench and Swing-SideAngle in the SPORTS ACTIONS dataset, and the vast majority of the event classes in the UCF50 dataset  ... 
arXiv:1204.3616v1 fatcat:rbdclkvncvg2tdbtx35unodps4

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
Fine-Grained Dataset and Its Efficient Semantic Segmentation for Unstructured Driving Scenarios DAY 2 -Jan 13, 2021 S, Anupama; Shedligeri, Prasan; Pal, Abhishek; Mitr, Kaushik 2186 Video Reconstruction  ...  CH4.2 Bag of freebies for fine-grained product recognition Day date Session code Session type Presentation mode Session start time Session end time Session chair/authors Paper id Also  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning [article]

Jiahao Wang, Yunhong Wang, Sheng Liu, Annan Li
2021 pre-print
Furthermore, to fairly compare different models, we establish specific benchmark protocols on two large-scale fine-grained action recognition datasets.  ...  Therefore, we propose the few-shot fine-grained action recognition problem, aiming to recognize novel fine-grained actions with only few samples given for each class.  ...  proposed large-scale fine-grained action datasets, i.e.  ... 
doi:10.1145/3474085.3475216 arXiv:2108.06647v1 fatcat:vqgnlnojwzabpk7fqcmwfadtuu

Animating Arbitrary Objects via Deep Motion Transfer

Aliaksandr Siarohin, Stephane Lathuiliere, Sergey Tulyakov, Elisa Ricci, Nicu Sebe
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We demonstrate the effectiveness of our method on several benchmark datasets, spanning a wide variety of object appearances, and show that our approach outperforms stateof-the-art image animation and video  ...  Given an input image with a target object and a driving video sequence depicting a moving object, our framework generates a video in which the target object is animated according to the driving sequence  ...  Similarly to the keypoint and the generator network, the use of U-Net architecture is motivated by the need of fine-grained details.  ... 
doi:10.1109/cvpr.2019.00248 dblp:conf/cvpr/SiarohinLT0S19 fatcat:quvi2lioefd3jlmaczmfgfd634

Maintaining Common Ground in Dynamic Environments

Takuma Udagawa, Akiko Aizawa
2021 Transactions of the Association for Computational Linguistics  
Based on our minimal task formulation, we collected a large-scale dataset of 5,617 dialogues to enable fine-grained evaluation and analysis of various dialogue systems.  ...  Through our dataset analyses, we highlight novel challenges introduced in our setting, such as the usage of complex spatio-temporal expressions to create and maintain common ground.  ...  Acknowledgments We are grateful to our action editor, Michel Galley, and the three anonymous reviewers for  ... 
doi:10.1162/tacl_a_00409 fatcat:ifrzbkqcfra6zcd56cuhhotdpe

Table of Contents

2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
cial Intelligence, University of Chinese Academy of Sciences) FineGym: A Hierarchical Video Dataset for Fine-Grained Action Understanding 2613DianShao (CUHK-SenseTime Joint Lab, The Chinese University  ...  and Evaluation Google Landmarks Dataset v2 -A Large-Scale Benchmark for Instance-Level Recognition and Retrieval 2572 Tobias Weyand (Google Research, USA) , André Araujo (Google Research, USA) , Bingyi  ... 
doi:10.1109/cvpr42600.2020.00004 fatcat:c7els2kee5cq7lh6cemeqhdcoa

Proceedings of the 79th Annual Meeting of the Japanese Society for Animal Psychology

2019 Japanese Journal of Animal Psychology  
Five sizes of grains were tested with a paired comparison method.  ...  We conducted a social preference test and a social recognition test.  ... 
doi:10.2502/janip.69.3.4 fatcat:kqmbiqmcdjh2nchj6iwj45yakm

Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations

Yunhe Xie, Kailai Yang, Chengjie Sun, Bingquan Liu, Zhenzhou Ji
2021 Findings of the Association for Computational Linguistics: EMNLP 2021   unpublished
Specifically, we use a self-matching module for internal utterance-knowledge inter- Unlike vanilla emotion recognition of sentences, action.  ...  which to the token “cheap”, the model manages to label will shift the fine-grained emotions corresponding the utterance “Angry”, which is also  ... 
doi:10.18653/v1/2021.findings-emnlp.245 fatcat:fh44kc76ovcb3jw4uedluhjnzi

Proceedings of the 74th Annual Meeting of the Japanese Society for Animal Psychology

2014 Japanese Journal of Animal Psychology  
Grain weight (g) and energy per grain (kcal) of each grain were as follows: soybean (0.240g, 0.847kcal), corn (0.161g, 0.564kcal), mixed feed (0.070g, 0.251kcal), safflower (0.053g, 0.222kcal) and sorghum  ...  By inserting fine optic fibers into the DRN, we delivered yellow light into the DRN during aggressive behavior.  ...  In the training phase, the rats were required to go to a goal box from a start box in a lattice maze. There were 5 trials in a daily session.  ... 
doi:10.2502/janip.64.2.5 fatcat:daez5kvyinfgxa5ojyq4uiijce

Quantitative assessment of spatial sound distortion by the semi-ideal recording point of a hear-through device

Pablo Hoffmann, Flemming Christensen, Dorte Hammersho/i
2013 Journal of the Acoustical Society of America  
and grain size.  ...  This dynamic system receives as inputs a target state and a set of parameters that tune the system to the desired action.  ...  Luis A.  ... 
doi:10.1121/1.4805375 fatcat:u4bvxh6karet3avpjdhpfwqpf4
« Previous Showing results 1 — 15 out of 25 results