Ziyi Liu

Dong-Ho Lee, Akshen Kadakia, Brihi Joshi et al. · meta-ai

NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model. While existing model debugging methods have shown promise, their prototype-level implementations provide limited practical utility. Thus, we propose XMD: the first open-source, end-to-end framework for explanation-based model debugging. Given task- or instance-level explanations, users can flexibly provide various forms of feedback via an intuitive, web-based UI. After receiving user feedback, XMD automatically updates the model in real time, by regularizing the model so that its explanations align with the user feedback. The new model can then be easily deployed into real-world applications via Hugging Face. Using XMD, we can improve the model's OOD performance on text classification tasks by up to 18%.

Brihi Joshi, Aaron Chan, Ziyi Liu et al. · meta-ai

By explaining how humans would solve a given task, human rationales can provide strong learning signal for neural language models (LMs). Explanation regularization (ER) aims to improve LM generalization by pushing the LM's machine rationales (Which input tokens did the LM focus on?) to align with human rationales (Which input tokens would humans focus on?). Though prior works primarily study ER via in-distribution (ID) evaluation, out-of-distribution (OOD) generalization is often more critical in real-world scenarios, yet ER's effect on OOD generalization has been underexplored. In this paper, we introduce ER-Test, a framework for evaluating ER models' OOD generalization along three dimensions: unseen dataset tests, contrast set tests, and functional tests. Using ER-Test, we extensively analyze how ER models' OOD generalization varies with different ER design choices. Across two tasks and six datasets, ER-Test shows that ER has little impact on ID performance but can yield large OOD performance gains. Also, we find that ER can improve OOD performance even with limited rationale supervision. ER-Test's results help demonstrate ER's utility and establish best practices for using ER effectively.

Jesse Zhang, Jiahui Zhang, Karl Pertsch et al.

We propose BOSS, an approach that automatically learns to solve new long-horizon, complex, and meaningful tasks by growing a learned skill library with minimal supervision. Prior work in reinforcement learning require expert supervision, in the form of demonstrations or rich reward functions, to learn long-horizon tasks. Instead, our approach BOSS (BOotStrapping your own Skills) learns to accomplish new tasks by performing "skill bootstrapping," where an agent with a set of primitive skills interacts with the environment to practice new skills without receiving reward feedback for tasks outside of the initial skill set. This bootstrapping phase is guided by large language models (LLMs) that inform the agent of meaningful skills to chain together. Through this process, BOSS builds a wide range of complex and useful behaviors from a basic set of primitive skills. We demonstrate through experiments in realistic household environments that agents trained with our LLM-guided bootstrapping procedure outperform those trained with naive bootstrapping as well as prior unsupervised skill acquisition methods on zero-shot execution of unseen, long-horizon tasks in new environments. Website at clvrai.com/boss.

Xue Yu, Ziyi Liu, Wu Wang et al.

This study investigates clustered federated learning (FL), one of the formulations of FL with non-i.i.d. data, where the devices are partitioned into clusters and each cluster optimally fits its data with a localized model. We propose a clustered FL framework that incorporates a nonconvex penalty to pairwise differences of parameters. Without a priori knowledge of the set of devices in each cluster and the number of clusters, this framework can autonomously estimate cluster structures. To implement the proposed framework, we introduce a novel clustered FL method called Fusion Penalized Federated Clustering (FPFC). Building upon the standard alternating direction method of multipliers (ADMM), FPFC can perform partial updates at each communication round and allows parallel computation with variable workload. These strategies significantly reduce the communication cost while ensuring privacy, making it practical for FL. We also propose a new warmup strategy for hyperparameter tuning in FL settings and explore the asynchronous variant of FPFC (asyncFPFC). Theoretical analysis provides convergence guarantees for FPFC with general losses and establishes the statistical convergence rate under a linear model with squared loss. Extensive experiments have demonstrated the superiority of FPFC compared to current methods, including robustness and generalization capability.

Jingjing Jiang, Ziyi Liu, Nanning Zheng

Benefiting from large-scale pretrained vision language models (VLMs), the performance of visual question answering (VQA) has approached human oracles. However, finetuning such models on limited data often suffers from overfitting and poor generalization issues, leading to a lack of model robustness. In this paper, we aim to improve input robustness from an information bottleneck perspective when adapting pretrained VLMs to the downstream VQA task. Input robustness refers to the ability of models to defend against visual and linguistic input variations, as well as shortcut learning involved in inputs. Generally, the representations obtained by pretrained VLMs inevitably contain irrelevant and redundant information for a specific downstream task, resulting in statistically spurious correlations and insensitivity to input variations. To encourage representations to converge to a minimal sufficient statistic in multimodal learning, we propose Correlation Information Bottleneck (CIB), which seeks a tradeoff between compression and redundancy in representations by minimizing the mutual information (MI) between inputs and representations while maximizing the MI between outputs and representations. Moreover, we derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations, incorporating different internal correlations that guide models to learn more robust representations and facilitate modality alignment. Extensive experiments consistently demonstrate the effectiveness and superiority of the proposed CIB in terms of input robustness and accuracy.

Ziyi Liu, Rakshitha Godahewa, Kasun Bandara et al.

Machine learning (ML) based time series forecasting models often require and assume certain degrees of stationarity in the data when producing forecasts. However, in many real-world situations, the data distributions are not stationary and they can change over time while reducing the accuracy of the forecasting models, which in the ML literature is known as concept drift. Handling concept drift in forecasting is essential for many ML methods in use nowadays, however, the prior work only proposes methods to handle concept drift in the classification domain. To fill this gap, we explore concept drift handling methods in particular for Global Forecasting Models (GFM) which recently have gained popularity in the forecasting domain. We propose two new concept drift handling methods, namely: Error Contribution Weighting (ECW) and Gradient Descent Weighting (GDW), based on a continuous adaptive weighting concept. These methods use two forecasting models which are separately trained with the most recent series and all series, and finally, the weighted average of the forecasts provided by the two models are considered as the final forecasts. Using LightGBM as the underlying base learner, in our evaluation on three simulated datasets, the proposed models achieve significantly higher accuracy than a set of statistical benchmarks and LightGBM baselines across four evaluation metrics.

Yusen Zhang, Zhongli Li, Qingyu Zhou et al.

To automatically correct handwritten assignments, the traditional approach is to use an OCR model to recognize characters and compare them to answers. The OCR model easily gets confused on recognizing handwritten Chinese characters, and the textual information of the answers is missing during the model inference. However, teachers always have these answers in mind to review and correct assignments. In this paper, we focus on the Chinese cloze tests correction and propose a multimodal approach (named AiM). The encoded representations of answers interact with the visual information of students' handwriting. Instead of predicting 'right' or 'wrong', we perform the sequence labeling on the answer text to infer which answer character differs from the handwritten content in a fine-grained way. We take samples of OCR datasets as the positive samples for this task, and develop a negative sample augmentation method to scale up the training data. Experimental results show that AiM outperforms OCR-based methods by a large margin. Extensive studies demonstrate the effectiveness of our multimodal approach.

Runtao Liu, Ziyi Liu, Jiaqi Tang et al.

Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets, weakening temporal grounding and missing fine-grained cues. We propose a multi-agent framework in which a master LLM coordinates a grounding agent to localize question-relevant segments and a vision agent to extract targeted textual observations. The master agent plans with a step limit, and is trained with reinforcement learning to encourage concise, correct, and efficient multi-agent cooperation. This design helps the master agent focus on relevant clips via grounding, complements subtitles with visual detail, and yields interpretable trajectories. On our proposed LongTVQA and LongTVQA+ which are episode-level datasets aggregated from TVQA/TVQA+, our multi-agent system significantly outperforms strong non-agent baselines. Experiments also show reinforcement learning further strengthens reasoning and planning for the trained agent. Code and data will be shared at https://longvideoagent.github.io/.

Ziyi Liu, Dengpan Ye, Long Tang et al.

With the development of artificial intelligence, neural networks play a key role in network intrusion detection systems (NIDS). Despite the tremendous advantages, neural networks are susceptible to adversarial attacks. To improve the reliability of NIDS, many research has been conducted and plenty of solutions have been proposed. However, the existing solutions rarely consider the adversarial attacks against recurrent neural networks (RNN) with time steps, which would greatly affect the application of NIDS in real world. Therefore, we first propose a novel RNN adversarial attack model based on feature reconstruction called \textbf{T}emporal adversarial \textbf{E}xamples \textbf{A}ttack \textbf{M}odel \textbf{(TEAM)}, which applied to time series data and reveals the potential connection between adversarial and time steps in RNN. That is, the past adversarial examples within the same time steps can trigger further attacks on current or future original examples. Moreover, TEAM leverages Time Dilation (TD) to effectively mitigates the effect of temporal among adversarial examples within the same time steps. Experimental results show that in most attack categories, TEAM improves the misjudgment rate of NIDS on both black and white boxes, making the misjudgment rate reach more than 96.68%. Meanwhile, the maximum increase in the misjudgment rate of the NIDS for subsequent original samples exceeds 95.57%.

Yunming Zhang, Dengpan Ye, Caiyun Xie et al.

The malicious applications of deep forgery, represented by face swapping, have introduced security threats such as misinformation dissemination and identity fraud. While some research has proposed the use of robust watermarking methods to trace the copyright of facial images for post-event traceability, these methods cannot effectively prevent the generation of forgeries at the source and curb their dissemination. To address this problem, we propose a novel comprehensive active defense mechanism that combines traceability and adversariality, called Dual Defense. Dual Defense invisibly embeds a single robust watermark within the target face to actively respond to sudden cases of malicious face swapping. It disrupts the output of the face swapping model while maintaining the integrity of watermark information throughout the entire dissemination process. This allows for watermark extraction at any stage of image tracking for traceability. Specifically, we introduce a watermark embedding network based on original-domain feature impersonation attack. This network learns robust adversarial features of target facial images and embeds watermarks, seeking a well-balanced trade-off between watermark invisibility, adversariality, and traceability through perceptual adversarial encoding strategies. Extensive experiments demonstrate that Dual Defense achieves optimal overall defense success rates and exhibits promising universality in anti-face swapping tasks and dataset generalization ability. It maintains impressive adversariality and traceability in both original and robust settings, surpassing current forgery defense methods that possess only one of these capabilities, including CMUA-Watermark, Anti-Forgery, FakeTagger, or PGD methods.

Jingjing Jiang, Ziyi Liu, Yifan Liu et al.

Encouraging progress has been made towards Visual Question Answering (VQA) in recent years, but it is still challenging to enable VQA models to adaptively generalize to out-of-distribution (OOD) samples. Intuitively, recompositions of existing visual concepts (\ie, attributes and objects) can generate unseen compositions in the training set, which will promote VQA models to generalize to OOD samples. In this paper, we formulate OOD generalization in VQA as a compositional generalization problem and propose a graph generative modeling-based training scheme (X-GGM) to implicitly model the problem. X-GGM leverages graph generative modeling to iteratively generate a relation matrix and node representations for the predefined graph that utilizes attribute-object pairs as nodes. Furthermore, to alleviate the unstable training issue in graph generative modeling, we propose a gradient distribution consistency loss to constrain the data distribution with adversarial perturbations and the generated distribution. The baseline VQA model (LXMERT) trained with the X-GGM scheme achieves state-of-the-art OOD performance on two standard VQA OOD benchmarks, \ie, VQA-CP v2 and GQA-OOD. Extensive ablation studies demonstrate the effectiveness of X-GGM components. Code is available at \url{https://github.com/jingjing12110/x-ggm}.

Jie Yang, Ziyi Liu, Ulian Shahnovich et al.

In this paper, we present a novel tone mapping algorithm that can be used for displaying wide dynamic range (WDR) images on low dynamic range (LDR) devices. The proposed algorithm is mainly motivated by the logarithmic response and local adaptation features of the human visual system (HVS). HVS perceives luminance differently when under different adaptation levels, and therefore our algorithm uses functions built upon different scales to tone map pixels to different values. Functions of large scales are used to maintain image brightness consistency and functions of small scales are used to preserve local detail and contrast. An efficient method using local variance has been proposed to fuse the values of different scales and to remove artifacts. The algorithm utilizes integral images and integral histograms to reduce computation complexity and processing time. Experimental results show that the proposed algorithm can generate high brightness, good contrast, and appealing images that surpass the performance of many state-of-the-art tone mapping algorithms. This project is available at https://github.com/jieyang1987/ToneMapping-Based-on-Multi-scale-Histogram-Synthesis.

Jie Yang, Ziyi Liu, Mengchen Lin et al.

Wide dynamic range (WDR) images contain more scene details and contrast when compared to common images. However, it requires tone mapping to process the pixel values in order to display properly. The details of WDR images can diminish during the tone mapping process. In this work, we address the problem by combining a novel reformulated Laplacian pyramid and deep learning. The reformulated Laplacian pyramid always decompose a WDR image into two frequency bands where the low-frequency band is global feature-oriented, and the high-frequency band is local feature-oriented. The reformulation preserves the local features in its original resolution and condenses the global features into a low-resolution image. The generated frequency bands are reconstructed and fine-tuned to output the final tone mapped image that can display on the screen with minimum detail and contrast loss. The experimental results demonstrate that the proposed method outperforms state-of-the-art WDR image tone mapping methods. The code is made publicly available at https://github.com/linmc86/Deep-Reformulated-Laplacian-Tone-Mapping.

Yangcen Liu, Ziyi Liu, Yuanhao Zhai et al.

Weakly-supervised temporal action localization (WTAL) aims to recognize and localize action instances with only video-level labels. Despite the significant progress, existing methods suffer from severe performance degradation when transferring to different distributions and thus may hardly adapt to real-world scenarios . To address this problem, we propose the Generalizable Temporal Action Localization task (GTAL), which focuses on improving the generalizability of action localization methods. We observed that the performance decline can be primarily attributed to the lack of generalizability to different action scales. To address this problem, we propose STAT (Self-supervised Temporal Adaptive Teacher), which leverages a teacher-student structure for iterative refinement. Our STAT features a refinement module and an alignment module. The former iteratively refines the model's output by leveraging contextual information and helps adapt to the target scale. The latter improves the refinement process by promoting a consensus between student and teacher models. We conduct extensive experiments on three datasets, THUMOS14, ActivityNet1.2, and HACS, and the results show that our method significantly improves the Baseline methods under the cross-distribution evaluation setting, even approaching the same-distribution evaluation performance.

Isabelle Lee, Joshua Lum, Ziyi Liu et al.

While interpretability research has shed light on some internal algorithms utilized by transformer-based LLMs, reasoning in natural language, with its deep contextuality and ambiguity, defies easy categorization. As a result, formulating clear and motivating questions for circuit analysis that rely on well-defined in-domain and out-of-domain examples required for causal interventions is challenging. Although significant work has investigated circuits for specific tasks, such as indirect object identification (IOI), deciphering natural language reasoning through circuits remains difficult due to its inherent complexity. In this work, we take initial steps to characterize causal reasoning in LLMs by analyzing clear-cut cause-and-effect sentences like "I opened an umbrella because it started raining," where causal interventions may be possible through carefully crafted scenarios using GPT-2 small. Our findings indicate that causal syntax is localized within the first 2-3 layers, while certain heads in later layers exhibit heightened sensitivity to nonsensical variations of causal sentences. This suggests that models may infer reasoning by (1) detecting syntactic cues and (2) isolating distinct heads in the final layers that focus on semantic relationships.

Yuanhao Zhai, Ziyi Liu, Zhenyu Wu et al.

Deep learning models have a risk of utilizing spurious clues to make predictions, such as recognizing actions based on the background scene. This issue can severely degrade the open-set action recognition performance when the testing samples have different scene distributions from the training samples. To mitigate this problem, we propose a novel method, called Scene-debiasing Open-set Action Recognition (SOAR), which features an adversarial scene reconstruction module and an adaptive adversarial scene classification module. The former prevents the decoder from reconstructing the video background given video features, and thus helps reduce the background information in feature learning. The latter aims to confuse scene type classification given video features, with a specific emphasis on the action foreground, and helps to learn scene-invariant information. In addition, we design an experiment to quantify the scene bias. The results indicate that the current open-set action recognizers are biased toward the scene, and our proposed SOAR method better mitigates such bias. Furthermore, our extensive experiments demonstrate that our method outperforms state-of-the-art methods, and the ablation studies confirm the effectiveness of our proposed modules.

Brihi Joshi, Ziyi Liu, Sahana Ramnath et al.

Among the remarkable emergent capabilities of large language models (LMs) is free-text rationalization; beyond a certain scale, large LMs are capable of generating seemingly useful rationalizations, which in turn, can dramatically enhance their performances on leaderboards. This phenomenon raises a question: can machine generated rationales also be useful for humans, especially when lay humans try to answer questions based on those machine rationales? We observe that human utility of existing rationales is far from satisfactory, and expensive to estimate with human studies. Existing metrics like task performance of the LM generating the rationales, or similarity between generated and gold rationales are not good indicators of their human utility. While we observe that certain properties of rationales like conciseness and novelty are correlated with their human utility, estimating them without human involvement is challenging. We show that, by estimating a rationale's helpfulness in answering similar unseen instances, we can measure its human utility to a better extent. We also translate this finding into an automated score, GEN-U, that we propose, which can help improve LMs' ability to generate rationales with better human utility, while maintaining most of its task performance. Lastly, we release all code and collected data with this project.

Jingjing Jiang, Ziyi Liu, Nanning Zheng

Video Question Answering (VideoQA), aiming to correctly answer the given question based on understanding multi-modal video content, is challenging due to the rich video content. From the perspective of video understanding, a good VideoQA framework needs to understand the video content at different semantic levels and flexibly integrate the diverse video content to distill question-related content. To this end, we propose a Lightweight Visual-Linguistic Reasoning framework named LiVLR. Specifically, LiVLR first utilizes the graph-based Visual and Linguistic Encoders to obtain multi-grained visual and linguistic representations. Subsequently, the obtained representations are integrated with the devised Diversity-aware Visual-Linguistic Reasoning module (DaVL). The DaVL considers the difference between the different types of representations and can flexibly adjust the importance of different types of representations when generating the question-related joint representation, which is an effective and general representation integration method. The proposed LiVLR is lightweight and shows its performance advantage on two VideoQA benchmarks, MRSVTT-QA and KnowIT VQA. Extensive ablation studies demonstrate the effectiveness of LiVLR key components.

Ziyi Liu, Jiaqi Zhang, Yongshuai Hou et al.

Background: Electronic Health Records (EHRs) contain rich information of patients' health history, which usually include both structured and unstructured data. There have been many studies focusing on distilling valuable information from structured data, such as disease codes, laboratory test results, and treatments. However, relying on structured data only might be insufficient in reflecting patients' comprehensive information and such data may occasionally contain erroneous records. Objective: With the recent advances of machine learning (ML) and deep learning (DL) techniques, an increasing number of studies seek to obtain more accurate results by incorporating unstructured free-text data as well. This paper reviews studies that use multimodal data, i.e. a combination of structured and unstructured data, from EHRs as input for conventional ML or DL models to address the targeted tasks. Materials and Methods: We searched in the Institute of Electrical and Electronics Engineers (IEEE) Digital Library, PubMed, and Association for Computing Machinery (ACM) Digital Library for articles related to ML-based multimodal EHR studies. Results and Discussion: With the final 94 included studies, we focus on how data from different modalities were combined and interacted using conventional ML and DL techniques, and how these algorithms were applied in EHR-related tasks. Further, we investigate the advantages and limitations of these fusion methods and indicate future directions for ML-based multimodal EHR research.

Ziyi Liu, Minghui Liao, Fulin luo et al.

Single-cell sequencing has a significant role to explore biological processes such as embryonic development, cancer evolution, and cell differentiation. These biological properties can be presented by a two-dimensional scatter plot. However, single-cell sequencing data generally has very high dimensionality. Therefore, dimensionality reduction should be used to process the high dimensional sequencing data for 2D visualization and subsequent biological analysis. The traditional dimensionality reduction methods, which do not consider the structure characteristics of single-cell sequencing data, are difficult to reveal the data structure in the 2D representation. In this paper, we develop a 2D feature representation method based on graph convolutional networks (GCN) for the visualization of single-cell data, termed single-cell sequencing graph embedding networks (SGEN). This method constructs the graph by the similarity relationship between cells and adopts GCN to analyze the neighbor embedding information of samples, which makes the similar cell closer to each other on the 2D scatter plot. The results show SGEN achieves obvious 2D distribution and preserves the high-dimensional relationship of different cells. Meanwhile, similar cell clusters have spatial continuity rather than relying heavily on random initialization, which can reflect the trajectory of cell development in this scatter plot.

Ziyi Liu, Jie Yang, Svetlana Yanushkevich et al.

Deep convolutional neural networks (DCNNs) have aided high dynamic range (HDR) imaging recently and have received a lot of attention. The quality of DCNN-generated HDR images has overperformed the traditional counterparts. However, DCNNs are prone to be computationally intensive and power-hungry, and hence cannot be implemented on various embedded computing platforms with limited power and hardware resources. Embedded systems have a huge market, and utilizing DCNNs' powerful functionality into them will further reduce human intervention. To address the challenge, we propose LightFuse, a lightweight CNN-based algorithm for extreme dual-exposure image fusion, which achieves better functionality than a conventional DCNN and can be deployed in embedded systems. Two sub-networks are utilized: a GlobalNet (G) and a DetailNet (D). The goal of G is to learn the global illumination information on the spatial dimension, whereas D aims to enhance local details on the channel dimension. Both G and D are based solely on depthwise convolution (D_Conv) and pointwise convolution (P_Conv) to reduce required parameters and computations. Experimental results show that this proposed technique could generate HDR images in extremely exposed regions with sufficient details to be legible. Our model outperforms other state-of-the-art approaches in peak signal-to-noise ratio (PSNR) score by 0.9 to 8.7 while achieving 16.7 to 306.2 times parameter reduction.

Ziyi Liu, Le Wang, Wei Tang et al.

Weakly-supervised Temporal Action Localization (WS-TAL) methods learn to localize temporal starts and ends of action instances in a video under only video-level supervision. Existing WS-TAL methods rely on deep features learned for action recognition. However, due to the mismatch between classification and localization, these features cannot distinguish the frequently co-occurring contextual background, i.e., the context, and the actual action instances. We term this challenge action-context confusion, and it will adversely affect the action localization accuracy. To address this challenge, we introduce a framework that learns two feature subspaces respectively for actions and their context. By explicitly accounting for action visual elements, the action instances can be localized more precisely without the distraction from the context. To facilitate the learning of these two feature subspaces with only video-level categorical labels, we leverage the predictions from both spatial and temporal streams for snippets grouping. In addition, an unsupervised learning task is introduced to make the proposed module focus on mining temporal information. The proposed approach outperforms state-of-the-art WS-TAL methods on three benchmarks, i.e., THUMOS14, ActivityNet v1.2 and v1.3 datasets.

Ziyi Liu, Le Wang, Qilin Zhang et al.

The object of Weakly-supervised Temporal Action Localization (WS-TAL) is to localize all action instances in an untrimmed video with only video-level supervision. Due to the lack of frame-level annotations during training, current WS-TAL methods rely on attention mechanisms to localize the foreground snippets or frames that contribute to the video-level classification task. This strategy frequently confuse context with the actual action, in the localization result. Separating action and context is a core problem for precise WS-TAL, but it is very challenging and has been largely ignored in the literature. In this paper, we introduce an Action-Context Separation Network (ACSNet) that explicitly takes into account context for accurate action localization. It consists of two branches (i.e., the Foreground-Background branch and the Action-Context branch). The Foreground- Background branch first distinguishes foreground from background within the entire video while the Action-Context branch further separates the foreground as action and context. We associate video snippets with two latent components (i.e., a positive component and a negative component), and their different combinations can effectively characterize foreground, action and context. Furthermore, we introduce extended labels with auxiliary context categories to facilitate the learning of action-context separation. Experiments on THUMOS14 and ActivityNet v1.2/v1.3 datasets demonstrate the ACSNet outperforms existing state-of-the-art WS-TAL methods by a large margin.

Jie Yang, Mengchen Lin, Ziyi Liu et al.

Wide dynamic range (WDR) image tone mapping is in high demand in many applications like film production, security monitoring, and photography. It is especially crucial for mobile devices because most of the images taken today are from mobile phones, hence such technology is highly demanded in the consumer market of mobile devices and is essential for a good customer experience. However, high-quality and high-performance WDR image tone mapping implementations are rarely found in the mobile-end. In this paper, we introduce a high performance, mobile-end WDR image tone mapping implementation. It leverages the tone mapping results of multiple receptive fields and calculates a suitable value for each pixel. The utilization of integral image and integral histogram significantly reduce the required computation. Moreover, GPU parallel computation is used to increase the processing speed. The experimental results indicate that our implementation can process a high-resolution WDR image within a second on mobile devices and produce appealing image quality.

Ziyi Liu, Jie Yang, Mengchen Lin et al.

Currently, face detection approaches focus on facial information by varying specific parameters including pose, occlusion, lighting, background, race, and gender. These studies only utilized the information obtained from low dynamic range images, however, face detection in wide dynamic range (WDR) scenes has received little attention. To our knowledge, there is no publicly available WDR database for face detection research. To facilitate and support future face detection research in the WDR field, we propose the first WDR database for face detection, called WDR FACE, which contains a total of 398 16-bit megapixel grayscale wide dynamic range images collected from 29 subjects. These WDR images (WDRIs) were taken in eight specific WDR scenes. The dynamic range of 90% images surpasses 60,000:1, and that of 70% images exceeds 65,000:1. Furthermore, we show the effect of different face detection procedures on the WDRIs in our database. This is done with 25 different tone mapping operators and five different face detectors. We provide preliminary experimental results of face detection on this unique WDR database.

Ziyi Liu, Giannis Karamanolakis, Daniel Hsu et al.

Health departments have been deploying text classification systems for the early detection of foodborne illness complaints in social media documents such as Yelp restaurant reviews. Current systems have been successfully applied for documents in English and, as a result, a promising direction is to increase coverage and recall by considering documents in additional languages, such as Spanish or Chinese. Training previous systems for more languages, however, would be expensive, as it would require the manual annotation of many documents for each new target language. To address this challenge, we consider cross-lingual learning and train multilingual classifiers using only the annotations for English-language reviews. Recent zero-shot approaches based on pre-trained multi-lingual BERT (mBERT) have been shown to effectively align languages for aspects such as sentiment. Interestingly, we show that those approaches are less effective for capturing the nuances of foodborne illness, our public health application of interest. To improve performance without extra annotations, we create artificial training documents in the target language through machine translation and train mBERT jointly for the source (English) and target language. Furthermore, we show that translating labeled documents to multiple languages leads to additional performance improvements for some target languages. We demonstrate the benefits of our approach through extensive experiments with Yelp restaurant reviews in seven languages. Our classifiers identify foodborne illness complaints in multilingual reviews from the Yelp Challenge dataset, which highlights the potential of our general approach for deployment in health departments.

Jinliang Zang, Le Wang, Ziyi Liu et al.

Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs). However, effective and efficient methods for incorporation of temporal information into CNNs are still being actively explored in the recent literature. Motivated by the popular recurrent attention models in the research area of natural language processing, we propose the Attention-based Temporal Weighted CNN (ATW), which embeds a visual attention model into a temporal weighted multi-stream CNN. This attention model is simply implemented as temporal weighting yet it effectively boosts the recognition performance of video representations. Besides, each stream in the proposed ATW framework is capable of end-to-end training, with both network parameters and temporal weights optimized by stochastic gradient descent (SGD) with backpropagation. Our experiments show that the proposed attention mechanism contributes substantially to the performance gains with the more discriminative snippets by focusing on more relevant video segments.