Search

In this paper, we introduce PoseCrafter, a one-shot method for personalized video generation following the control of flexible poses. Built upon Stable Diffusion and ControlNet, we carefully design an inference process to produce high-quality videos without the corresponding ground-truth frames. First, we select an appropriate reference frame from the training video and invert it to initialize all latent variables for generation. Then, we insert the corresponding training pose into the target pose sequences to enhance faithfulness through a trained temporal attention module. Furthermore, to alleviate the face and hand degradation resulting from discrepancies between poses of training videos and inference poses, we implement simple latent editing through an affine transformation matrix involving facial and hand landmarks. Extensive experiments on several datasets demonstrate that PoseCrafter achieves superior results to baselines pre-trained on a vast collection of videos under 8 commonly used metrics. Besides, PoseCrafter can follow poses from different individuals or artificial edits and simultaneously retain the human identity in an open-domain training video. Our project page is available at https://ml-gsai.github.io/PoseCrafter-demo/.

Xiaoxue Zhang,1 Xuyi Zhang,2 Xiaofeng Yu2 1School of Journalism and Communication, Tsinghua University, Beijing, People’s Republic of China; 2School of Media and Communication, Shenzhen University, Shenzhen, People’s Republic of ChinaCorrespondence: Xiaofeng Yu, Email yxfyxx1115@163.comIntroduction: Classic old movies and TV series (COMTS) can evoke individuals’ memories from the past. “Personality traits-motivation-behavior” is a theoretical frame to understand that nostalgia can lead to repeated watching behavior.Methods: We adopted an online survey to investigate the relationship between personality traits, nostalgia, social connectedness and the behavioral intention of repeated watching with those who re-watched movies or TV series (N = 645).Results: Our results showed that open, agreeable and neurotic individuals were more likely to feel nostalgic and then have the behavioral intention of repeated watching. In addition, for agreeable and neurotic individuals, social connectedness plays a mediating role in the relationship between these personality traits and behavioral intention of repeated watching.Keywords: personalities traits, motivation theory, social connectedness, nostalgia arousal, behavioral intention of repeated watching

Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels, which produces additional noise harmful to the performance of networks. Motivated by this, we present a simple yet effective cross ensemble knowledge distillation (CEKD) model for fine-grained feature learning. We innovatively propose a cross distillation module to provide additional supervision to alleviate the noise problem, and propose a collaborative ensemble module to overcome the target conflict problem. The proposed model can be trained in an end-to-end manner, and only requires image-level label supervision. Extensive experiments on widely used fine-grained benchmarks demonstrate the effectiveness of our proposed model. Specifically, with the backbone of ResNet-101, CEKD obtains the accuracy of 89.59%, 95.96% and 94.56% in three datasets respectively, outperforming state-of-the-art API-Net by 0.99%, 1.06% and 1.16%.

Jianxia Ma,1,* Jianqin Sun,2,* Huijing Bai,2 Houlian Ma,1 Ke Wang,1 Jun Wang,1 Xiaofeng Yu,1 Yiru Pan,3 Jianfeng Yao1 1Department of Gastroenterology, Huadong Hospital Affiliated to Fudan University, Shanghai, People’s Republic of China; 2Clinical Nutrition Center, Huadong Hospital Affiliated to Fudan University, Shanghai, People’s Republic of China; 3Clinical Laboratory, Huadong Hospital Affiliated to Fudan University, Shanghai, People’s Republic of China*These authors contributed equally to this workCorrespondence: Jianfeng Yao, Department of Gastroenterology, Huadong Hospital Affiliated to Fudan University, No. 221. Road West Yanan, Shanghai, 200040, People’s Republic of China, Tel +862162483180, Email yjf1966@126.comPurpose: This study was to explore the influence of flax seeds on the gut microbiota of elderly patients with functional constipation.Patients and Methods: Sixty elderly patients (68.68± 8.73 years) with functional constipation were recruited between January 2018 and March 2018. They received oral flax seeds (50 g/d) for one month. Bowel habits and adverse events were recorded before and after treatment. Fresh stool was collected before and after treatment and the amplification product of 16S rRNA V5 region was sequenced using the next-generation sequencing technique on the Ion Torrent PGM platform. The gut microbiota were analyzed before and after flax seeds treatment in the same subject.Results: Flax-seed treatment significantly increased the frequency of defecation and decreased abdominal distension in elderly patients with chronic constipation. The majority of gut bacteria belonged to the phyla of Firmicutes, Bacteroidetes, and Proteobacteria, accounting for 98.71%. After flax seeds treatment, the diversity of bacterial clusters significantly increased with increases of Roseburia_hominis, Pseudomonas_azotoformans, uncultured_Clostridiales_bacterium, Blautia_obeum, Ruminococcus_sp._16442, Pyramidobacter_piscolens

Jiaxi Zhao, Yiqin Huang, Xiaofeng Yu Huadong Hospital Affiliated to Fudan University, Shanghai, People’s Republic of ChinaCorrespondence: Xiaofeng Yu Tel +86 181 21227529Email yuxiaofeng252@163.comAbstract: Sarcopenia is a multifactorial disease related to aging, chronic inflammation, insufficient nutrition, and physical inactivity. Previous studies have suggested that there is a relationship between sarcopenia and gut microbiota,namely, the gut-muscle axis. The present review highlights that the gut microbiota can affect muscle mass and muscle function from inflammation and immunity,substance and energy metabolism, endocrine and insulin sensitivity, etc., directly or indirectly establishing a connection with sarcopenia, thereby realizing the “gut-muscle axis”.Keywords: gut microbiota, metabolism, inflammation, muscle

Xiaofeng Yu,* Xiaoxue Zhang* School of Media and Communication, Shenzhen University, Shenzhen, People’s Republic of China*These authors contributed equally to this workCorrespondence: Xiaofeng Yu Tel + 86 135 38148118Email yxfyxx1115@szu.edu.cnIntroduction: Nowadays, more and more people choose to rent houses in first-tier cities together with other people, which can alleviate certain economic pressure. Therefore co-tenancy has become an important field of academic research in recent years and a number of previous studies have discussed the phenomenon. However, fewer studies explore the influence of different variables on the willingness of co-tenancy behavior through quantitative methods.Methods: This study conceptualizes and implements concepts such as trust, positive emotion, relationship strength, satisfaction, income, duration of co-tenancy required and the willingness of co-tenancy behavior(WOCB). We designed and collected a questionnaire and finally a questionnaire survey of users (n=525) was conducted, and a basic description and comparison of research objects’ willingness of co-tenancy behavior were made in terms of trust, and positive emotion, relationship strength and monthly income also affect the willingness of co-tenancy behavior.Results: The trust effects have a positive impact on the WOCB, Trust effect will affect Relationship Strength and Positive Emotion, and will further affect the WOCB. However, this influence is negative when people are in high Monthly Income and negative when people are in low Monthly Income.Discussion: Trust, relationship strength and positive emotion are key factors for people to rent houses with others. That is to say, the intensity of people’s willingness to rent houses with others depends on the degree of trust in others, the relationship strength and positive emotion. When the post-90s drifters in Shenzhen do not believe others, they will tend to live alone rather than the new model of co-ten

We present the results for CAPRI Round 30, the first joint CASP-CAPRI experiment, which brought together experts from the protein structure prediction and protein-protein docking communities. The Round comprised 25 targets from amongst those submitted for the CASP11 prediction experiment of 2014. The targets included mostly homodimers, a few homotetramers, and two heterodimers, and comprised protein chains that could readily be modeled using templates from the Protein Data Bank. On average 24 CAPRI groups and 7 CASP groups submitted docking predictions for each target, and 12 CAPRI groups per target participated in the CAPRI scoring experiment. In total more than 9500 models were assessed against the 3D structures of the corresponding target complexes. Results show that the prediction of homodimer assemblies by homology modeling techniques and docking calculations is quite successful for targets featuring large enough subunit interfaces to represent stable associations. Targets with ambiguous or inaccurate oligomeric state assignments, often featuring crystal contact-sized interfaces, represented a confounding factor. For those, a much poorer prediction performance was achieved, while nonetheless often providing helpful clues on the correct oligomeric state of the protein. The prediction performance was very poor for genuine tetrameric targets, where the inaccuracy of the homology-built subunit models and the smaller pair-wise interfaces severely limited the ability to derive the correct assembly mode. Our analysis also shows that docking procedures tend to perform better than standard homology modeling techniques and that highly accurate models of the protein components are not always required to identify their association modes with acceptable accuracy. Proteins 2016; 84(Suppl 1):323-348. © 2016 Wiley Periodicals, Inc.

We present the results for CAPRI Round 30, the first joint CASP-CAPRI experiment, which brought together experts from the protein structure prediction and protein–protein docking communities. The Round comprised 25 targets from amongst those submitted for the CASP11 prediction experiment of 2014. The targets included mostly homodimers, a few homotetramers, and two heterodimers, and comprised protein chains that could readily be modeled using templates from the Protein Data Bank. On average 24 CAPRI groups and 7 CASP groups submitted docking predictions for each target, and 12 CAPRI groups per target participated in the CAPRI scoring experiment. In total more than 9500 models were assessed against the 3D structures of the corresponding target complexes. Results show that the prediction of homodimer assemblies by homology modeling techniques and docking calculations is quite successful for targets featuring large enough subunit interfaces to represent stable associations. Targets with ambiguous or inaccurate oligomeric state assignments, often featuring crystal contact-sized interfaces, represented a confounding factor. For those, a much poorer prediction performance was achieved, while nonetheless often providing helpful clues on the correct oligomeric state of the protein. The prediction performance was very poor for genuine tetrameric targets, where the inaccuracy of the homology-built subunit models and the smaller pair-wise interfaces severely limited the ability to derive the correct assembly mode. Our analysis also shows that docking procedures tend to perform better than standard homology modeling techniques and that highly accurate models of the protein components are not always required to identify their association modes with acceptable accuracy., We are most grateful to the PDBe at the European Bioinformatics Institute in Hinxton, UK, for hosting the CAPRI website. Our deepest thanks go to all the structural biologists and to the following structural genomics initiatives: Northeast Structural Genomics Consortium, Joint Center for Structural Genomics, NatPro PSI:Biology, New York Structural Genomics Research Center, Midwest Center for Structural Genomics, Structural Genomics Consortium, for contributing the targets for this joint CASP-CAPRI experiment. MFL acknowledges support from the FRABio FR3688 Research Federation “Structural & Functional Biochemistry of Biomolecular Assemblies.”, Peer Reviewed, Postprint (published version)

Based on these observations and analysis, we propose a joint discriminative probabilistic framework to optimize all relevant subtasks simultaneously. This framework defines a joint probability distribution for both segmentations in sequence data and relations of segments in the form of an exponential family. This model allows tight interactions between segmentations and relations of segments and it offers a natural way for IE tasks. Since exact parameter estimation and inference are prohibitively intractable, a structured variational inference algorithm is developed to perform parameter estimation approximately. For inference, we propose a strong bi-directional MH approach to find the MAP assignments for joint segmentations and relations to explore mutual benefits on both directions, such that segmentations can aid relations, and vice-versa., Information Extraction (IE) aims at identifying specific pieces of information (data) in a unstructured or semi-structured textual document and transforming unstructured information in a corpus of documents or Web pages into a structured database. There are several representative tasks in IE: named entity recognition (NER), which aims at identifying phrases that denote types of named entities, entity relation extraction, which aims at discovering the events or relations related to the entities, and the task of coreference resolution, aims at determining whether two extracted mentions of entities refer to the same object. IE is useful for a wide variety of applications., The end-to-end performance of high-level IE systems for compound tasks is often hampered by the use of cascaded frameworks. The integrated model we proposed can alleviate some of these problems, but it is only loosely coupled. Parameter estimation is performed independently and it only allows information to flow in one direction. In this top-down integration model, the decision of the bottom sub-model could guide the decision of the upper sub-model, but not vice-versa. Thus, deep interactions and dependencies between different tasks can hardly be well captured., We have investigated and developed a cascaded framework in an attempt to consider entity extraction and qualitative domain knowledge based on undirected, discriminatively-trained probabilistic graphical models. This framework consists of two stages and it is the combination of statistical learning and first-order logic. As a pipeline model, the first stage is a base model and the second stage is used to validate and correct the errors made in the base model. We incorporated domain knowledge that can be well formulated into first-order logic to extract entity candidates from the base model. We have applied this framework and achieved encouraging results in Chinese NER on the People's Daily corpus., We perform extensive experiments on three important IE tasks using real-world datasets, namely Chinese NER, entity identification and relationship extraction from Wikipedia's encyclopedic articles, and citation matching, to test our proposed models, including the bidirectional model, the integrated model, and the joint model. Experimental results show that our models significantly outperform current state-of-the-art probabilistic models, such as decoupled and joint models, illustrating the feasibility and promise of our proposed approaches. (Abstract shortened by UMI.), We present a general, strongly-coupled, and bidirectional architecture based on discriminatively trained factor graphs for information extraction, which consists of two components---segmentation and relation. First we introduce joint factors connecting variables of relevant subtasks to capture dependencies and interactions between them. We then propose a strong bidirectional Markov chain Monte Carlo (MCMC) sampling inference algorithm which allows information to flow in both directions to find the approximate maximum a posteriori (MAP) solution for all subtasks. Notably, our framework is considerably simpler to implement, and outperforms previous ones., Yu, Xiaofeng., Adviser: Zam Wai., Source: Dissertation Abstracts International, Volume: 72-04, Section: B, page: ., Thesis (Ph.D.)--Chinese University of Hong Kong, 2010., Includes bibliographical references (leaves 109-123)., Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web., Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web., also in Chinese., isbn: 9781124497891, Use of this resource is governed by the terms and conditions of the Creative Commons “Attribution-NonCommercial-NoDerivatives 4.0 International” License (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Based on these observations and analysis, we propose a joint discriminative probabilistic framework to optimize all relevant subtasks simultaneously. This framework defines a joint probability distribution for both segmentations in sequence data and relations of segments in the form of an exponential family. This model allows tight interactions between segmentations and relations of segments and it offers a natural way for IE tasks. Since exact parameter estimation and inference are prohibitively intractable, a structured variational inference algorithm is developed to perform parameter estimation approximately. For inference, we propose a strong bi-directional MH approach to find the MAP assignments for joint segmentations and relations to explore mutual benefits on both directions, such that segmentations can aid relations, and vice-versa., Information Extraction (IE) aims at identifying specific pieces of information (data) in a unstructured or semi-structured textual document and transforming unstructured information in a corpus of documents or Web pages into a structured database. There are several representative tasks in IE: named entity recognition (NER), which aims at identifying phrases that denote types of named entities, entity relation extraction, which aims at discovering the events or relations related to the entities, and the task of coreference resolution, aims at determining whether two extracted mentions of entities refer to the same object. IE is useful for a wide variety of applications., The end-to-end performance of high-level IE systems for compound tasks is often hampered by the use of cascaded frameworks. The integrated model we proposed can alleviate some of these problems, but it is only loosely coupled. Parameter estimation is performed independently and it only allows information to flow in one direction. In this top-down integration model, the decision of the bottom sub-model could guide the decision of the upper sub-model, but not vice-versa. Thus, deep interactions and dependencies between different tasks can hardly be well captured., We have investigated and developed a cascaded framework in an attempt to consider entity extraction and qualitative domain knowledge based on undirected, discriminatively-trained probabilistic graphical models. This framework consists of two stages and it is the combination of statistical learning and first-order logic. As a pipeline model, the first stage is a base model and the second stage is used to validate and correct the errors made in the base model. We incorporated domain knowledge that can be well formulated into first-order logic to extract entity candidates from the base model. We have applied this framework and achieved encouraging results in Chinese NER on the People's Daily corpus., We perform extensive experiments on three important IE tasks using real-world datasets, namely Chinese NER, entity identification and relationship extraction from Wikipedia's encyclopedic articles, and citation matching, to test our proposed models, including the bidirectional model, the integrated model, and the joint model. Experimental results show that our models significantly outperform current state-of-the-art probabilistic models, such as decoupled and joint models, illustrating the feasibility and promise of our proposed approaches. (Abstract shortened by UMI.), We present a general, strongly-coupled, and bidirectional architecture based on discriminatively trained factor graphs for information extraction, which consists of two components---segmentation and relation. First we introduce joint factors connecting variables of relevant subtasks to capture dependencies and interactions between them. We then propose a strong bidirectional Markov chain Monte Carlo (MCMC) sampling inference algorithm which allows information to flow in both directions to find the approximate maximum a posteriori (MAP) solution for all subtasks. Notably, our framework is considerably simpler to implement, and outperforms previous ones., Yu, Xiaofeng., Adviser: Zam Wai., Source: Dissertation Abstracts International, Volume: 72-04, Section: B, page: ., Thesis (Ph.D.)--Chinese University of Hong Kong, 2010., Includes bibliographical references (leaves 109-123)., Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web., Electronic reproduction. Ann Arbor, MI : ProQuest Information and Learning Company, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web., also in Chinese., isbn: 9781124497891, Use of this resource is governed by the terms and conditions of the Creative Commons “Attribution-NonCommercial-NoDerivatives 4.0 International” License (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Coreference resolution is regarded as a crucial step for acquiring linkages among pieces of information extracted. Traditionally, coreference resolution models make use of independent attribute-value features over pairs of noun phrases. However, dependency and deeper relations between features can more adequately describe the properties of coreference relations between noun phrases. In this paper, we propose a framework of coreference resolution based on first order logic and probabilistic graphical model, the Markov Logic Network. The proposed framework enables the use of background knowledge and captures more complex coreference linkage properties through rich expression of conditions. Moreover, the proposed conditions can capture the structural pattern within a noun phrase as well as contextual information between noun phrases. Our experiments show improvement with the use of the expressive logic models and the use of pattern-based conditions.

Coreference resolution is regarded as a crucial step for acquiring linkages among pieces of information extracted. Traditionally, coreference resolution models make use of independent attribute-value features over pairs of noun phrases. However, dependency and deeper relations between features can more adequately describe the properties of coreference relations between noun phrases. In this paper, we propose a framework of coreference resolution based on first order logic and probabilistic graphical model, the Markov Logic Network. The proposed framework enables the use of background knowledge and captures more complex coreference linkage properties through rich expression of conditions. Moreover, the proposed conditions can capture the structural pattern within a noun phrase as well as contextual information between noun phrases. Our experiments show improvement with the use of the expressive logic models and the use of pattern-based conditions.

We report an experiment in which a high-performance boosting based NER model originally designed for multiple European languages is instead applied to the Chinese named entity recognition task of the third SIGHAN Chinese language processing bakeoff. Using a simple character-based model along with a set of features that are easily obtained from the Chinese input strings, the system described employs boosting, a promising and theoretically well-founded machine learning method to combine a set of weak classifiers together into a final system. Even though we did no other Chinese-specific tuning, and used only one-third of the MSRA and CityU corpora to train the system, reasonable results are obtained. Our evaluation results show that 75.07 and 80.51 overall F-measures were obtained on MSRA and CityU test sets respectively.

We describe a machine translation approach being designed at HKUST to integrate semantic processing into statistical machine translation, beginning with entity and word sense disambiguation. We show how integrating the semantic modules consistently improves translation quality across several data sets. We report results on five different IWSLT 2006 speech translation tasks, representing HKUST's first participation in the IWSLT spoken language translation evaluation campaign. We translated both read and spontaneous speech transcriptions from Chinese to English, achieving reasonable performance despite the fact that our system is essentially text-based and therefore not designed and tuned to tackle the challenges of speech translation. We also find that the system achieves reasonable results on a wide range of languages, by evaluating on read speech transcriptions from Arabic, Italian, and Japanese into English.

We describe a machine translation approach being designed at HKUST to integrate semantic processing into statistical machine translation, beginning with entity and word sense disambiguation. We show how integrating the semantic modules consistently improves translation quality across several data sets. We report results on five different IWSLT 2006 speech translation tasks, representing HKUST's first participation in the IWSLT spoken language translation evaluation campaign. We translated both read and spontaneous speech transcriptions from Chinese to English, achieving reasonable performance despite the fact that our system is essentially text-based and therefore not designed and tuned to tackle the challenges of speech translation. We also find that the system achieves reasonable results on a wide range of languages, by evaluating on read speech transcriptions from Arabic, Italian, and Japanese into English.

We report an experiment in which a high-performance boosting based NER model originally designed for multiple European languages is instead applied to the Chinese named entity recognition task of the third SIGHAN Chinese language processing bakeoff. Using a simple character-based model along with a set of features that are easily obtained from the Chinese input strings, the system described employs boosting, a promising and theoretically well-founded machine learning method to combine a set of weak classifiers together into a final system. Even though we did no other Chinese-specific tuning, and used only one-third of the MSRA and CityU corpora to train the system, reasonable results are obtained. Our evaluation results show that 75.07 and 80.51 overall F-measures were obtained on MSRA and CityU test sets respectively.

We describe a machine translation approach being designed at HKUST to integrate semantic processing into statistical machine translation, beginning with entity and word sense disambiguation. We show how integrating the semantic modules consistently improves translation quality across several data sets. We report results on five different IWSLT 2006 speech translation tasks, representing HKUST's first participation in the IWSLT spoken language translation evaluation campaign. We translated both read and spontaneous speech transcriptions from Chinese to English, achieving reasonable performance despite the fact that our system is essentially text-based and therefore not designed and tuned to tackle the challenges of speech translation. We also find that the system achieves reasonable results on a wide range of languages, by evaluating on read speech transcriptions from Arabic, Italian, and Japanese into English.