Geographic health disparities pose a pressing global challenge, particularly in underserved regions of low- and middle-income nations. Addressing this issue requires a collaborative approach to enhance healthcare quality, leveraging support from medically more developed areas. Federated learning emerges as a promising tool for this purpose. However, the scarcity of medical data and limited computation resources in underserved regions make collaborative training of powerful machine learning models challenging. Furthermore, there exists an asymmetrical reciprocity between underserved and developed regions. To overcome these challenges, we propose a novel cross-silo federated learning framework, named FedHelp, aimed at alleviating geographic health disparities and fortifying the diagnostic capabilities of underserved regions. Specifically, FedHelp leverages foundational model knowledge via one-time API access to guide the learning process of underserved small clients, addressing the challenge of insufficient data. Additionally, we introduce a novel asymmetric dual knowledge distillation module to manage the issue of asymmetric reciprocity, facilitating the exchange of necessary knowledge between developed large clients and underserved small clients. We validate the effectiveness and utility of FedHelp through extensive experiments on both medical image classification and segmentation tasks. The experimental results demonstrate significant performance improvement compared to state-of-the-art baselines, particularly benefiting clients in underserved regions.

Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling. While various techniques address these computational challenges, a less-explored issue is designing an efficient and adaptable network backbone for iterative refinement. Current options like U-Net and Vision Transformer often rely on resource-intensive deep networks and lack the flexibility needed for generating images at variable resolutions or with a smaller network than used in training. This study introduces LEGO bricks, which seamlessly integrate Local-feature Enrichment and Global-content Orchestration. These bricks can be stacked to create a test-time reconfigurable diffusion backbone, allowing selective skipping of bricks to reduce sampling costs and generate higher-resolution images than the training data. LEGO bricks enrich local regions with an MLP and transform them using a Transformer block while maintaining a consistent full-resolution image across all bricks. Experimental results demonstrate that LEGO bricks enhance training efficiency, expedite convergence, and facilitate variable-resolution image generation while maintaining strong generative performance. Moreover, LEGO significantly reduces sampling time compared to other methods, establishing it as a valuable enhancement for diffusion models. Our code and project page are available at https://jegzheng.github.io/LEGODiffusion.

Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. Visual instruction fine-tuning (IFT) is a vital process for aligning MLLMs’ output with user’s intentions. High-quality and diversified instruction following data is the key to this fine-tuning process. Recent studies propose to construct visual IFT datasets through a multifaceted approach: transforming existing datasets with rule-based templates, employing GPT-4 for rewriting annotations, and utilizing GPT-4V for visual dataset pseudo-labeling. LLaVA-1.5 adopted similar approach and construct LLaVA-Instruct, which is one of the simplest, most widely used, yet most effective IFT datasets today. Notably, when properly fine-tuned with this dataset, MLLMs can achieve state-of-the-art performance on several benchmarks. However, we noticed that models trained with this dataset often struggle to follow user instructions properly in multi-round dialog. In addition, tradition caption and VQA evaluation benchmarks, with their closed-form evaluation structure, are not fully equipped to assess the capabilities of modern open-ended generative MLLMs. This problem is not unique to the LLaVA-Instruct dataset, but may be a potential issue in all IFT datasets constructed from image captioning or VQA sources, though the extent of this issue may vary. We argue that datasets with diverse and high-quality detailed instruction following annotations are essential and adequate for MLLMs IFT. In this work, we establish a new IFT dataset, with images sourced from the COCO dataset along with more diverse instructions. Our experiments show that when fine-tuned with proposed dataset, MLLMs achieve better performance on open-ended evaluation benchmarks in both single-round and multi-round dialog setting.

This paper presents FedType, a simple yet pioneering framework designed to fill research gaps in heterogeneous model aggregation within federated learning (FL). FedType introduces small identical proxy models for clients, serving as agents for information exchange, ensuring model security, and achieving efficient communication simultaneously. To transfer knowledge between large private and small proxy models on clients, we propose a novel uncertainty-based asymmetrical reciprocity learning method, eliminating the need for any public data. Comprehensive experiments conducted on benchmark datasets demonstrate the efficacy and generalization ability of FedType across diverse settings. Our approach redefines federated learning paradigms by bridging model heterogeneity, eliminating reliance on public data, prioritizing client privacy, and reducing communication costs (The codes are available in the supplementation materials).

Image restoration (IR) in real-world scenarios presents significant challenges due to the lack of high-capacity models and comprehensive datasets. To tackle these issues, we present a dual strategy: GenIR, an innovative data curation pipeline, and DreamClear, a cutting-edge Diffusion Transformer (DiT)-based image restoration model. **GenIR**, our pioneering contribution, is a dual-prompt learning pipeline that overcomes the limitations of existing datasets, which typically comprise only a few thousand images and thus offer limited generalizability for larger models. GenIR streamlines the process into three stages: image-text pair construction, dual-prompt based fine-tuning, and data generation \& filtering. This approach circumvents the laborious data crawling process, ensuring copyright compliance and providing a cost-effective, privacy-safe solution for IR dataset construction. The result is a large-scale dataset of one million high-quality images. Our second contribution, **DreamClear**, is a DiT-based image restoration model. It utilizes the generative priors of text-to-image (T2I) diffusion models and the robust perceptual capabilities of multi-modal large language models (MLLMs) to achieve photorealistic restoration. To boost the model's adaptability to diverse real-world degradations, we introduce the Mixture of Adaptive Modulator (MoAM). It employs token-wise degradation priors to dynamically integrate various restoration experts, thereby expanding the range of degradations the model can address. Our exhaustive experiments confirm DreamClear's superior performance, underlining the efficacy of our dual strategy for real-world image restoration. Code and pre-trained models are available at: https://github.com/shallowdream204/DreamClear.

In the realm of Multimodal Large Language Models (MLLMs), vision-language connector plays a crucial role to link the pre-trained vision encoders with Large Language Models (LLMs). Despite its importance, the vision-language connector has been relatively less explored. In this study, we aim to propose a strong vision-language connector that enables MLLM to simultaneously achieve high accuracy and low computation cost. We first reveal the existence of the visual anchors in Vision Transformer and propose a cost-effective search algorithm to progressively extract them. Building on these findings, we introduce the Anchor Former (AcFormer), a novel vision-language connector designed to leverage the rich prior knowledge obtained from these visual anchors during pretraining, guiding the aggregation of information. Through extensive experimentation, we demonstrate that the proposed method significantly reduces computational costs by nearly two-thirds, while simultaneously outperforming baseline methods. This highlights the effectiveness and efficiency of AcFormer.

Improving the generalization ability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge. Some theoretical studies have uncovered that DNNs have preferences for some frequency components in the learning process and indicated that this may affect the robustness of learned features. In this paper, we propose Deep Frequency Filtering (DFF)for learning domain-generalizable features, which is the first endeavour to explicitly modulate the frequency components of different transfer difficulties across domains in the latent space during training. To achieve this, we perform Fast Fourier Transform (FFT) for the feature maps at different layers, then adopt a light-weight module to learn attention masks from the frequency representations after FFT to enhance transferable components while suppressing the components not conducive to generalization. Further, we empirically compare the effectiveness of adopting different types of attention designs for implementing DFF. Extensive experiments demonstrate the effectiveness of our proposed DFF and show that applying our DFF on a plain baseline out-performs the state-of-the-art methods on different domain generalization tasks, including close-set classification and open-set retrieval.

Most efforts in unsupervised domain adaptation (UDA) focus on learning the domain-invariant representations between the two domains. However, such representations may still confuse two patterns due to the domain gap. Considering that semantic information is useful for the final task and domain information always indicates the discrepancy between two domains, to address this issue, we propose to decouple the representations of semantic features from domain features to reduce domain bias. Different from traditional methods, we adopt a simple but effective module with only one domain discriminator to decouple the representations, offering two benefits. Firstly, it eliminates the need for labeled sample pairs, making it more suitable for UDA. Secondly, without adversarial learning, our model can achieve a more stable training phase. Moreover, to further enhance the task-specific features, we employ a causal mechanism to separate semantic features related to causal factors from the overall feature representations. Specially, we utilize a dual-classifier strategy, where each classifier is fed with the entire features and the semantic features, respectively. By minimizing the discrepancy between the outputs of the two classifiers, the causal influence of the semantic features is accentuated. Experiments on several public datasets demonstrate the proposed model can outperform the state-of-the-art methods. Our code is available at: https://github.com/qzxRtY37/DRLC https://github.com/qzxRtY37/DRLC.

Tracking multiple objects in videos relies on modeling the spatial-temporal interactions of the objects. In this paper, we propose TransMOT, which leverages powerful graph transformers to efficiently model the spatial and temporal interactions among the objects. TransMOT is capable of effectively modeling the interactions of a large number of objects by arranging the trajectories of the tracked targets and detection candidates as a set of sparse weighted graphs, and constructing a spatial graph transformer encoder layer, a temporal transformer encoder layer, and a spatial graph transformer decoder layer based on the graphs. Through end-to-end learning, TransMOT can exploit the spatial-temporal clues to directly estimate association from a large number of loosely filtered detection predictions for robust MOT in complex scenes. The proposed method is evaluated on multiple benchmark datasets, including MOT15, MOT16, MOT17, and MOT20, and it achieves state-of-the-art performance on all the datasets.

Multi-camera tracking systems are gaining popularity in applications that demand high-quality tracking results, such as frictionless checkout. In cluttered and crowded environments, monocular multi-object tracking (MOT) systems often fail due to occlusions. Multiple highly overlapped cameras are capable of recovering partial 3D information. When used properly, 3D data can significantly alleviate the occlusion issue. However, training a multi-camera tracker demands a large-scale multi-camera tracking dataset with diverse camera settings and backgrounds. These requirements make the collection of multi-camera tracking dataset challenging and expensive. The cost of creating such a dataset has limited the availability and scale of datasets in this domain. Instead, we appeal to an auto-annotation system to reduce the cost, which uses overlapped and calibrated depth and RGB cameras to build a 3D tracker and automatically generates the 3D tracking results. The results are manually checked and corrected to ensure the label quality, which is much cheaper than solely manual annotation. Next, the 3D tracking results are projected to each calibrated RGB camera view to create 2D tracking results. In this way, we collect and annotate a large-scale densely labeled multi-camera tracking dataset from five different environments. We have conducted extensive experiments using two real-time multi-camera trackers and a person re-identification (ReID) model under different settings. This dataset provides a reliable benchmark for multi-camera, multi-object tracking systems in cluttered and crowded environments. We expect this benchmark to encourage more research attempts in this domain. Our dataset will be publicly released upon the acceptance of this work.

Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain data can be accessible all at once. However, for the real-world streaming data, this hinders the timely adaptation to changing data statistics and sufficient exploitation of increasing samples. In this paper, to address more practical scenarios, we propose a new task, Lifelong Un-supervised Domain Adaptive (LUDA) person ReID. This is challenging because it requires the model to continuously adapt to unlabeled data in the target environments while alleviating catastrophic forgetting for such a fine-grained person retrieval task. We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation. Specifically, a meta-based Coordinated Data Replay strategy is proposed to replay old data and update the network with a coordinated optimization direction for both adaptation and memorization. Moreover, we propose Relational Consistency Learning for old knowledge distillation/inheritance in line with the objective of retrieval-based tasks. We set up two evaluation settings to simulate the practical application scenarios. Extensive experiments demonstrate the effectiveness of our CLUDA-ReID for both scenarios with stationary target streams and scenarios with dynamic target streams.

Audio video scene-aware dialog (AVSD) is a new but more challenging visual question answering (VQA) task because of the higher complexity of feature extraction and fusion brought by the additional modalities. Although recent methods have achieved early success in improving feature extraction technique for AVSD, the technique of feature fusion still needs further investigation. In this paper, inspired by the success of self-attention mechanism and the importance of understanding questions for VQA answering, we propose a question-guided self-attentive multi-modal fusion network (QUALIFIER) to improve the AVSD practice in the stage of feature fusion and answer generation. Specifically, after extracting features and learning a comprehensive feature for each modality, we first use the designed self-attentive multi-modal fusion (SMF) module to aggregate each feature with the correlated information learned from others. Later, by prioritizing the question feature, we concatenate it with each fused feature to guide the generation of a natural language response to the question. As for experimental results, QUALIFIER shows better performance than other baseline methods in the large-scale AVSD dataset named DSTC7. Additionally, the human evaluation and ablation study results also demonstrate the effectiveness of our network architecture.

Xingyi Yang, Muchao Ye, Quanzeng You, Fenglong Ma. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

With the rapid development of social media, visual sentiment analysis from image or video has become a hot spot in visual understanding researches. In this work, we propose an effective approach using visual and textual fusion for sentiment analysis of short GIF videos with textual descriptions. We extract both sequence-level and frame-level visual features for each given GIF video. Next, we build a visual sentiment classifier by using the extracted features. We also define a mapping function, which converts the sentiment probability from the classifier to a sentiment score used in our fusion function. At the same time, for the accompanied textual annotations, we employ the Synset forest to extract the sets of the meaningful sentiment words and utilize the SentiWordNet3.0 model to obtain the textual sentiment score. Then, we design a joint visual-textual sentiment score function weighted with visual sentiment component and textual sentiment one. To make the function more robust, we introduce a noticeable difference threshold to further process the fused sentiment score. Finally, we adopt a grid search technique to obtain relevant model hyper-parameters by optimizing a sentiment aware score function. Experimental results and analysis extensively demonstrate the effectiveness of the proposed sentiment recognition scheme on three benchmark datasets including T-GIF dataset, GSO-2016 dataset and Adjusted-GIFGIF dataset.

Recognizing every person's action in a crowded and cluttered environment is a challenging task in computer vision. We propose to tackle this challenging problem using a holistic 4D ``scan'' of a cluttered scene to include every detail about the people and environment. This leads to a new problem, i.e., recognizing multiple people's actions in the cluttered 4D representation. At the first step, we propose a new method to track people in 4D, which can reliably detect and follow each person in real time. Then, we build a new deep neural network, the Action4DNet, to recognize the action of each tracked person. Such a model gives reliable and accurate results in the real-world settings. We also design an adaptive 3D convolution layer and a novel discriminative temporal feature learning objective to further improve the performance of our model. Our method is invariant to camera view angles, resistant to clutter and able to handle crowd. The experimental results show that the proposed method is fast, reliable and accurate. Our method paves the way to action recognition in the real-world applications and is ready to be deployed to enable smart homes, smart factories and smart stores.

Chatbot has become an important solution to rapidly increasing customer care demands on social media in recent years. However, current work on chatbot for customer care ignores a key to impact user experience - tones. In this work, we create a novel tone-aware chatbot that generates toned responses to user requests on social media. We first conduct a formative research, in which the effects of tones are studied. Significant and various influences of different tones on user experience are uncovered in the study. With the knowledge of effects of tones, we design a deep learning based chatbot that takes tone information into account. We train our system on over 1.5 million real customer care conversations collected from Twitter. The evaluation reveals that our tone-aware chatbot generates as appropriate responses to user requests as human agents. More importantly, our chatbot is perceived to be even more empathetic than human agents.

The goal of diagnosis prediction task is to predict the future health information of patients from their historical Electronic Healthcare Records (EHR). The most important and challenging problem of diagnosis prediction is to design an accurate, robust and interpretable predictive model. Existing work solves this problem by employing recurrent neural networks (RNNs) with attention mechanisms, but these approaches suffer from the data sufficiency problem. To obtain good performance with insufficient data, graph-based attention models are proposed. However, when the training data are sufficient, they do not offer any improvement in performance compared with ordinary attention-based models. To address these issues, we propose KAME, an end-to-end, accurate and robust model for predicting patients' future health information. KAME not only learns reasonable embeddings for nodes in the knowledge graph, but also exploits general knowledge to improve the prediction accuracy with the proposed knowledge attention mechanism. With the learned attention weights, KAME allows us to interpret the importance of each piece of knowledge in the graph. Experimental results on three real world datasets show that the proposed KAME significantly improves the prediction performance compared with the state-of-the-art approaches, guarantees the robustness with both sufficient and insufficient data, and learns interpretable disease representations.

Semantic embeddings for images and sentences have been widely studied recently. The ability of deep neural networks on learning rich and robust visual and textual representations offers the opportunity to develop effective semantic embedding models. Currently, the state-of-the-art approaches in semantic learning first employ deep neural networks to encode images and sentences into a common semantic space. Then, the learning objective is to ensure a larger similarity between matching image and sentence pairs than randomly sampled pairs. Usually, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) are employed for learning image and sentence representations, respectively. On one hand, CNNs are known to produce robust visual features at different levels and RNNs are known for capturing dependencies in sequential data. Therefore, this simple framework can be sufficiently effective in learning visual and textual semantics. On the other hand, different from CNNs, RNNs cannot produce middle-level (e.g. phrase-level in text) representations. As a result, only global representations are available for semantic learning. This could potentially limit the performance of the model due to the hierarchical structures in images and sentences. In this work, we apply Convolutional Neural Networks to process both images and sentences. Consequently, we can employ mid-level representations to assist global semantic learning by introducing a new learning objective on the convolutional layers. The experimental results show that our proposed textual CNN models with the new learning objective lead to better performance than the state-of-the-art approaches.

Predicting the risk of potential diseases from Electronic Health Records (EHR) has attracted considerable attention in recent years, especially with the development of deep learning techniques. Compared with traditional machine learning models, deep learning based approaches achieve superior performance on risk prediction task. However, none of existing work explicitly takes prior medical knowledge (such as the relationships between diseases and corresponding risk factors) into account. In medical domain, knowledge is usually represented by discrete and arbitrary rules. Thus, how to integrate such medical rules into existing risk prediction models to improve the performance is a challenge. To tackle this challenge, we propose a novel and general framework called PRIME for risk prediction task, which can successfully incorporate discrete prior medical knowledge into all of the state-of-the-art predictive models using posterior regularization technique. Different from traditional posterior regularization, we do not need to manually set a bound for each piece of prior medical knowledge when modeling desired distribution of the target disease on patients. Moreover, the proposed PRIME can automatically learn the importance of different prior knowledge with a log-linear model.Experimental results on three real medical datasets demonstrate the effectiveness of the proposed framework for the task of risk prediction

Sentiment analysis on large-scale social media data is important to bridge the gaps between social media contents and real world activities including political election prediction, individual and public emotional status monitoring and analysis, and so on. Although textual sentiment analysis has been well studied based on platforms such as Twitter and Instagram, analysis of the role of extensive emoji uses in sentiment analysis remains light. In this paper, we propose a novel scheme for Twitter sentiment analysis with extra attention on emojis. We first learn bi-sense emoji embeddings under positive and negative sentimental tweets individually, and then train a sentiment classifier by attending on these bi-sense emoji embeddings with an attention-based long short-term memory network (LSTM). Our experiments show that the bi-sense embedding is effective for extracting sentiment-aware embeddings of emojis and outperforms the state-of-the-art models. We also visualize the attentions to show that the bi-sense emoji embedding provides better guidance on the attention mechanism to obtain a more robust understanding of the semantics and sentiments.

Visual sentiment analysis, which studies the emotional response of humans on visual stimuli such as images and videos, has been an interesting and challenging problem. It tries to understand the high-level content of visual data. The success of current models can be attributed to the development of robust algorithms from computer vision. Most of the existing models try to solve the problem by proposing either robust features or more complex models. In particular, visual features from the whole image or video are the main proposed inputs. Little attention has been paid to local areas, which we believe is pretty relevant to human's emotional response to the whole image. In this work, we study the impact of local image regions on visual sentiment analysis. Our proposed model utilizes the recent studied attention mechanism to jointly discover the relevant local regions and build a sentiment classifier on top of these local regions. The experimental results suggest that 1) our model is capable of automatically discovering sentimental local regions of given images and 2) it outperforms existing state-of-the-art algorithms to visual sentiment analysis.

Sentiment analysis is crucial for extracting social signals from social media content. Due to the prevalence of images in social media, image sentiment analysis is receiving increasing attention in recent years. However, most existing systems are black-boxes that do not provide insight on how image content invokes sentiment and emotion in the viewers. On the other hand, psychological studies have confirmed that salient objects in an image often invoke emotions. In this work, we investigate more fine-grained and more comprehensive interaction between visual saliency and visual sentiment. In particular, we partition images in several meta-level scene-type dimensions that are relevant to most images, including: open-closed, natural-manmade, indoor-outdoor, and face-noface. Facilitated by state of the art saliency detection algorithm and sentiment classification algorithm, we examine how the sentiment of the salient region(s) in an image relates to the overall sentiment of the image. The experiments on a representative image emotion dataset have shown interesting correlation between saliency and sentiment in different scene types and shed light on the mechanism of visual sentiment evocation.

Predicting the future health information of patients from the historical Electronic Health Records (EHR) is a core research task in the development of personalized healthcare. Patient EHR data consist of sequences of visits over time, where each visit contains multiple medical codes, including diagnosis, medication, and procedure codes. The most important challenges for this task are to model the temporality and high dimensionality of sequential EHR data and to interpret the prediction results. Existing work solves this problem by employing recurrent neural networks (RNNs) to model EHR data and utilizing simple attention mechanism to interpret the results. However, RNN-based approaches suffer from the problem that the performance of RNNs drops when the length of sequences is large, and the relationships between subsequent visits are ignored by current RNN-based approaches. To address these issues, we propose Dipole, an end-to-end, simple and robust model for predicting patients' future health information. Dipole employs bidirectional recurrent neural networks to remember all the information of both the past visits and the future visits, and it introduces three attention mechanisms to measure the relationships of different visits for the prediction. With the attention mechanisms, Dipole can interpret the prediction results effectively. Dipole also allows us to interpret the learned medical code representations which are confirmed positively by medical experts. Experimental results on two real world EHR datasets show that the proposed Dipole can significantly improve the prediction accuracy compared with the state-of-the-art diagnosis prediction approaches and provide clinically meaningful interpretation.

Social multimedia refers to the multimedia content (text, images, and videos) generated by social network users for social interactions. The increasing popularity of online social networks leads to a significant amount of multimedia content generated by online social network users. Researchers from both the industrial and academic have been working on a broad range of projects related to the analyzing and understanding the online multimedia content, including real world activity prediction and content recommendation. Particularly, understanding online users' opinions or sentiments is a fundamental task that can benefit many applications, such as political campaigning and commercial marketing. We present a few recent advances in social multimedia sentiment analysis. Specifically, this tutorial consists of three parts. The first part is on visual sentiment analysis. We will introduce the task of visual sentiment, its main challenges, and the state-of-the-art approaches. We will include several representative approaches to manually designing visual features for this task as well as some approaches using deep neural networks. The second part is on building multimedia sentiment analysis datasets. We will introduce the challenges, the solutions in the construction of different large-scale datasets for sentiment analysis. The final part is mainly on multimodality model for sentiment analysis. We will introduce some recent research projects on multimodality designing and learning. In addition, we will also share some applications of sentiment analysis, as well as thoughts on current challenges and future directions.

Initializing an effective dictionary is an indispensable step for sparse representation. In this paper, we focus on the dictionary selection problem with the objective to select a compact subset of basis from original training data instead of learning a new dictionary matrix as dictionary learning models do. We first design a new dictionary selection model via l2,0norm. For model optimization, we propose two methods: one is the standard forward-backward greedy algorithm, which is not suitable for large-scale problems; the other is based on the gradient cues at each forward iteration and speeds up the process dramatically. In comparison with the state-of-the-art dictionary selection models, our model is not only more effective and efficient, but also can control the sparsity. To evaluate the performance of our new model, we select two practical web media summarization problems: 1) we build a new data set consisting of around 500 users, 3000 albums, and 1 million images, and achieve effective assisted albuming based on our model and 2) by formulating the video summarization problem as a dictionary selection issue, we employ our model to extract keyframes from a video sequence in a more flexible way. Generally, our model outperforms the state-of-the-art methods in both these two tasks.

Real estate appraisal, which is the process of estimating the price for real estate properties, is crucial for both buyers and sellers as the basis for negotiation and transaction. Traditionally, the repeat sales model has been widely adopted to estimate real estate prices. However, it depends on the design and calculation of a complex economic-related index, which is challenging to estimate accurately. Today, real estate brokers provide easy access to detailed online information on real estate properties to their clients. We are interested in estimating the real estate price from these large amounts of easily accessed data. In particular, we analyze the prediction power of online house pictures, which is one of the key factors for online users to make a potential visiting decision. The development of robust computer vision algorithms makes the analysis of visual content possible. In this paper, we employ a recurrent neural network to predict real estate prices using the state-of-the-art visual features. The experimental results indicate that our model outperforms several other state-of-the-art baseline algorithms in terms of both mean absolute error and mean absolute percentage error.

Psychological research results have confirmed that people can have different emotional reactions to different visual stimuli. Several papers have been published on the problem of visual emotion analysis. In particular, attempts have been made to analyze and predict people's emotional reaction towards images. To this end, different kinds of hand-tuned features are proposed. The results reported on several carefully selected and labeled small image data sets have confirmed the promise of such features. While the recent successes of many computer vision related tasks are due to the adoption of Convolutional Neural Networks (CNNs), visual emotion analysis has not achieved the same level of success. This may be primarily due to the unavailability of confidently labeled and relatively large image data sets for visual emotion analysis. In this work, we introduce a new data set, which started from 3+ million weakly labeled images of different emotions and ended up 30 times as large as the current largest publicly available visual emotion data set. We hope that this data set encourages further research on visual emotion analysis. We also perform extensive benchmarking analyses on this large data set using the state of the art methods including CNNs.

Psychologists have demonstrated that pets have a positive impact on owners' happiness. For example, lonely people are often advised to have a dog or cat to quell their social isolation. Conventional psychological research methods of analyzing this phenomenon are mostly based on surveys or self-reported questionnaires, which are time-consuming and lack of scalability. Utilizing social media as an alternative and complimentary resource could potentially address both issues and provide different perspectives on this psychological investigation. In this paper, we propose a novel and effective approach that exploits social media to study the effect of pets on owners' happiness. The proposed framework includes three major components: (1) collecting user-level data from Instagram consisting of about 300,000 images from 2905 users; (2) constructing a convolutional neural network (CNN) for pets classification, and combined with timeline information, further identifying pet owners and the control group; (3) measuring the confidence score of happiness by detecting and analyzing selfie images. Furthermore, various factors of demographics are employed to analyze the fine-grained effects of pets on happiness. Our experimental results demonstrate the effectiveness of the proposed approach and we believe that this approach can be applied to other related domains as a large-scale, high-confidence methodology of user activity analysis through social media.

Automatically generating a natural language description of an image has attracted interests recently both because of its importance in practical applications and because it connects two major artificial intelligence fields: computer vision and natural language processing. Existing approaches are either top-down, which start from a gist of an image and convert it into words, or bottom-up, which come up with words describing various aspects of an image and then combine them. In this paper, we propose a new algorithm that combines both approaches through a model of semantic attention. Our algorithm learns to selectively attend to semantic concept proposals and fuse them into hidden states and outputs of recurrent neural networks. The selection and fusion form a feedback connecting the top-down and bottom-up computation. We evaluate our algorithm on two public benchmarks: Microsoft COCO and Flickr30K. Experimental results show that our algorithm significantly outperforms the state-of-the-art approaches consistently across different evaluation metrics.

Online social networks have attracted the attention from both the academia and real world. In particular, the rich multimedia information accumulated in recent years provides an easy and convenient way for more active communication between people. This offers an opportunity to research people's behaviors and activities based on those multimedia content. One emerging area is driven by the fact that these massive multimedia data contain people's daily sentiments and opinions. However, existing sentiment analysis typically focuses on textual information regardless of the visual content, which may be as informative in expressing people's sentiments and opinions. In this research, we attempt to analyze the online sentiment changes of social media users using both the textual and visual content. Nowadays, social media networks such as Twitter have become major platforms of information exchange and communication between users, with tweets as the common information carrier. As an old saying has it, an image is worth a thousand words. The image tweet is a great example of multimodal sentiment. In this research, we focus on sentiment analysis based on visual and multimedia information analysis. We will review the state-of-the-art in this topic. Several of our projects related to this research area will also be discussed. Experimental results are included to demonstrate and summarize our contributions.

Sentiment analysis is crucial for extracting social signals from social media content. Due to huge variation in social media, the performance of sentiment classifiers using single modality (visual or textual) still lags behind satisfaction. In this paper, we propose a new framework that integrates textual and visual information for robust sentiment analysis. Different from previous work, we believe visual and textual information should be treated jointly in a structural fashion. Our system first builds a semantic tree structure based on sentence parsing, aimed at aligning textual words and image regions for accurate analysis. Next, our system learns a robust joint visual-textual semantic representation by incorporating 1) an attention mechanism with LSTM (long short term memory) and 2) an auxiliary semantic learning task. Extensive experimental results on several known data sets show that our method outperforms existing the state-of-the-art joint models in sentiment analysis. We also investigate different tree-structured LSTM (T-LSTM) variants and analyze the effect of the attention mechanism in order to provide deeper insight on how the attention mechanism helps the learning of the joint visual-textual sentiment classifier.

Sentiment analysis of online user generated content is important for many social media analytics tasks. Researchers have largely relied on textual sentiment analysis to develop systems to predict political elections, measure economic indicators, and so on. Recently, social media users are increasingly using additional images and videos to express their opinions and share their experiences. Sentiment analysis of such large-scale textual and visual content can help better extract user sentiments toward events or topics. Motivated by the needs to leverage large-scale social multimedia content for sentiment analysis, we propose a cross-modality consistent regression (CCR) model, which is able to utilize both the state-of-the-art visual and textual sentiment analysis techniques. We first fine-tune a convolutional neural network (CNN) for image sentiment analysis and train a paragraph vector model for textual sentiment analysis. On top of them, we train our multi-modality regression model. We use sentimental queries to obtain half a million training samples from Getty Images. We have conducted extensive experiments on both machine weakly labeled and manually labeled image tweets. The results show that the proposed model can achieve better performance than the state-of-the-art textual and visual sentiment analysis algorithms alone.

Sampling is the key aspect for Nyström extension based spectral clustering. Traditional sampling schemes select the set of landmark points on a whole and focus on how to lower the matrix approximation error. However, the matrix approximation error does not have direct impact on the clustering performance. In this article, we propose a sampling framework from an incremental perspective, i.e., the landmark points are selected one by one, and each next point to be sampled is determined by previously selected landmark points. Incremental sampling builds explicit relationships among landmark points; thus, they work together well and provide a theoretical guarantee on the clustering performance. We provide two novel analysis methods and propose two schemes for selecting-the-next-one of the framework. The first scheme is based on clusterability analysis, which provides a better guarantee on clustering performance than schemes based on matrix approximation error analysis. The second scheme is based on loss analysis, which provides maximized predictive ability of the landmark points on the (implicit) labels of the unsampled points. Experimental results on a wide range of benchmark datasets demonstrate the superiorities of our proposed incremental sampling schemes over existing sampling schemes.

Sentiment analysis of online user generated content is important for many social media analytics tasks. Researchers have largely relied on textual sentiment analysis to develop systems to predict political elections, measure economic indicators, and so on. Recently, social media users are increasingly using images and videos to express their opinions and share their experiences. Sentiment analysis of such large scale visual content can help better extract user sentiments toward events or topics, such as those in image tweets, so that prediction of sentiment from visual content is complementary to textual sentiment analysis. Motivated by the needs in leveraging large scale yet noisy training data to solve the extremely challenging problem of image sentiment analysis, we employ Convolutional Neural Networks (CNN). We first design a suitable CNN architecture for image sentiment analysis. We obtain half a million training samples by using a baseline sentiment algorithm to label Flickr images. To make use of such noisy machine labeled data, we employ a progressive strategy to fine-tune the deep network. Furthermore, we improve the performance on Twitter images by inducing domain transfer with a small number of manually labeled Twitter images. We have conducted extensive experiments on manually labeled Twitter images. The results show that the proposed CNN can achieve better performance in image sentiment analysis than competing algorithms.

Sentiment analysis of online user generated content is important for many social media analytics tasks. Researchers have largely relied on textual sentiment analysis to develop systems to predict political elections, measure economic indicators, and so on. Recently, social media users are increasingly using additional images and videos to express their opinions and share their experiences. Sentiment analysis of such large-scale textual and visual content can help better extract user sentiments toward events or topics. Motivated by the needs to leverage large-scale social multimedia content for sentiment analysis, we utilize both the state-of-the-art visual and textual sentiment analysis techniques for joint visual-textual sentiment analysis. We first fine-tune a convolutional neural network (CNN) for image sentiment analysis and train a paragraph vector model for textual sentiment analysis. We have conducted extensive experiments on both machine weakly labeled and manually labeled image tweets. The results show that joint visual-textual features can achieve the state-of-the-art performance than textual and visual sentiment analysis algorithms alone.

Compared with real-world polling, election prediction based on social media can be far more timely and cost-effective due to the immediate availability of fast evolving Web contents. However, information from social media may suffer from noise and sampling bias that are caused by various factors and thus pose one of biggest challenges in social media-based data analytics. This paper presents a new model, named competitive vector auto regression (CVAR), to build a reliable forecasting system for the US presidential elections and US House race. Our CVAR model is designed to analyze the correlation between image-centric social multimedia and real-world phenomena. By introducing the competition mechanism, CVAR compares the popularity among multiple competing candidates. More importantly , CVAR is able to combine visual information with textual information from rich and multifaceted social multimedia, which helps extract reliable signals and mitigate sampling bias. As a result, our proposed system can 1) accurately predict the election outcome, 2) infer the sentiment of the candidate photos shared in the social media communities, and 3) account for the sentiment of viewer comments towards the candidates on the related images. The experiments on the 2012 US presidential election at both national and state levels, as well as the 2014 US House race, have demonstrated the power and promise of the proposed approach.

To alleviate the memory and computational burdens of spectral clustering for large scale problems, some kind of low-rank matrix approximation is usually employed. Nyström method is an efficient technique to generate low rank matrix approximation and its most important aspect is sampling. The matrix approximation errors of several sampling schemes have been theoretically analyzed for a number of learning tasks. However, the impact of matrix approximation error on the clustering performance of spectral clustering has not been studied. In this paper, we firstly analyze the performance of Nyström method in terms of cluster ability, thus answer the impact of matrix approximation error on the clustering performance of spectral clustering. Our analysis immediately suggests an incremental sampling scheme for the Nyström method based spectral clustering. Experimental results show that the proposed incremental sampling scheme outperforms existing sampling schemes on various clustering tasks and image segmentation applications, and its efficiency is comparable with existing sampling schemes.