Yuan Zong

Cheng Lu, Wenming Zheng, Hailun Lian et al.

Spectrogram is commonly used as the input feature of deep neural networks to learn the high(er)-level time-frequency pattern of speech signal for speech emotion recognition (SER). \textcolor{black}{Generally, different emotions correspond to specific energy activations both within frequency bands and time frames on spectrogram, which indicates the frequency and time domains are both essential to represent the emotion for SER. However, recent spectrogram-based works mainly focus on modeling the long-term dependency in time domain, leading to these methods encountering the following two issues: (1) neglecting to model the emotion-related correlations within frequency domain during the time-frequency joint learning; (2) ignoring to capture the specific frequency bands associated with emotions.} To cope with the issues, we propose an attentive time-frequency neural network (ATFNN) for SER, including a time-frequency neural network (TFNN) and time-frequency attention. Specifically, aiming at the first issue, we design a TFNN with a frequency-domain encoder (F-Encoder) based on the Transformer encoder and a time-domain encoder (T-Encoder) based on the Bidirectional Long Short-Term Memory (Bi-LSTM). The F-Encoder and T-Encoder model the correlations within frequency bands and time frames, respectively, and they are embedded into a time-frequency joint learning strategy to obtain the time-frequency patterns for speech emotions. Moreover, to handle the second issue, we also adopt time-frequency attention with a frequency-attention network (F-Attention) and a time-attention network (T-Attention) to focus on the emotion-related frequency band ranges and time frame ranges, which can enhance the discriminability of speech emotion features.

Yan Zhao, Jincen Wang, Yuan Zong et al.

In this paper, we propose a novel deep transfer learning method called deep implicit distribution alignment networks (DIDAN) to deal with cross-corpus speech emotion recognition (SER) problem, in which the labeled training (source) and unlabeled testing (target) speech signals come from different corpora. Specifically, DIDAN first adopts a simple deep regression network consisting of a set of convolutional and fully connected layers to directly regress the source speech spectrums into the emotional labels such that the proposed DIDAN can own the emotion discriminative ability. Then, such ability is transferred to be also applicable to the target speech samples regardless of corpus variance by resorting to a well-designed regularization term called implicit distribution alignment (IDA). Unlike widely-used maximum mean discrepancy (MMD) and its variants, the proposed IDA absorbs the idea of sample reconstruction to implicitly align the distribution gap, which enables DIDAN to learn both emotion discriminative and corpus invariant features from speech spectrums. To evaluate the proposed DIDAN, extensive cross-corpus SER experiments on widely-used speech emotion corpora are carried out. Experimental results show that the proposed DIDAN can outperform lots of recent state-of-the-art methods in coping with the cross-corpus SER tasks.

Jie Zhu, Yuan Zong, Jingang Shi et al.

This paper focuses on the research of micro-expression recognition (MER) and proposes a flexible and reliable deep learning method called learning to rank onset-occurring-offset representations (LTR3O). The LTR3O method introduces a dynamic and reduced-size sequence structure known as 3O, which consists of onset, occurring, and offset frames, for representing micro-expressions (MEs). This structure facilitates the subsequent learning of ME-discriminative features. A noteworthy advantage of the 3O structure is its flexibility, as the occurring frame is randomly extracted from the original ME sequence without the need for accurate frame spotting methods. Based on the 3O structures, LTR3O generates multiple 3O representation candidates for each ME sample and incorporates well-designed modules to measure and calibrate their emotional expressiveness. This calibration process ensures that the distribution of these candidates aligns with that of macro-expressions (MaMs) over time. Consequently, the visibility of MEs can be implicitly enhanced, facilitating the reliable learning of more discriminative features for MER. Extensive experiments were conducted to evaluate the performance of LTR3O using three widely-used ME databases: CASME II, SMIC, and SAMM. The experimental results demonstrate the effectiveness and superior performance of LTR3O, particularly in terms of its flexibility and reliability, when compared to recent state-of-the-art MER methods.

Xiaolin Xu, Yuan Zong, Wenming Zheng et al.

In this paper, we present a large-scale, multi-source, and unconstrained database called SDFE-LV for spotting the onset and offset frames of a complete dynamic facial expression from long videos, which is known as the topic of dynamic facial expression spotting (DFES) and a vital prior step for lots of facial expression analysis tasks. Specifically, SDFE-LV consists of 1,191 long videos, each of which contains one or more complete dynamic facial expressions. Moreover, each complete dynamic facial expression in its corresponding long video was independently labeled for five times by 10 well-trained annotators. To the best of our knowledge, SDFE-LV is the first unconstrained large-scale database for the DFES task whose long videos are collected from multiple real-world/closely real-world media sources, e.g., TV interviews, documentaries, movies, and we-media short videos. Therefore, DFES tasks on SDFE-LV database will encounter numerous difficulties in practice such as head posture changes, occlusions, and illumination. We also provided a comprehensive benchmark evaluation from different angles by using lots of recent state-of-the-art deep spotting methods and hence researchers interested in DFES can quickly and easily get started. Finally, with the deep discussions on the experimental evaluation results, we attempt to point out several meaningful directions to deal with DFES tasks and hope that DFES can be better advanced in the future. In addition, SDFE-LV will be freely released for academic use only as soon as possible.

Sunan Li, Hailun Lian, Cheng Lu et al.

The emotion recognition has attracted more attention in recent decades. Although significant progress has been made in the recognition technology of the seven basic emotions, existing methods are still hard to tackle compound emotion recognition that occurred commonly in practical application. This article introduces our achievements in the 7th Field Emotion Behavior Analysis (ABAW) competition. In the competition, we selected pre trained ResNet18 and Transformer, which have been widely validated, as the basic network framework. Considering the continuity of emotions over time, we propose a time pyramid structure network for frame level emotion prediction. Furthermore. At the same time, in order to address the lack of data in composite emotion recognition, we utilized fine-grained labels from the DFEW database to construct training data for emotion categories in competitions. Taking into account the characteristics of valence arousal of various complex emotions, we constructed a classification framework from coarse to fine in the label space.

Liu Liu, Guang Li, Dingfan Deng et al.

In this letter, we aim to investigate whether laboratory rats' pain can be automatically assessed through their facial expressions. To this end, we began by presenting a publicly available dataset called RatsPain, consisting of 1,138 facial images captured from six rats that underwent an orthodontic treatment operation. Each rat' facial images in RatsPain were carefully selected from videos recorded either before or after the operation and well labeled by eight annotators according to the Rat Grimace Scale (RGS). We then proposed a novel deep learning method called PainSeeker for automatically assessing pain in rats via facial expressions. PainSeeker aims to seek pain-related facial local regions that facilitate learning both pain discriminative and head pose robust features from facial expression images. To evaluate the PainSeeker, we conducted extensive experiments on the RatsPain dataset. The results demonstrate the feasibility of assessing rats' pain from their facial expressions and also verify the effectiveness of the proposed PainSeeker in addressing this emerging but intriguing problem. The RasPain dataset can be freely obtained from https://github.com/xhzongyuan/RatsPain.

Deng Li, Xin Liu, Bohao Xing et al.

Emotion AI is the ability of computers to understand human emotional states. Existing works have achieved promising progress, but two limitations remain to be solved: 1) Previous studies have been more focused on short sequential video emotion analysis while overlooking long sequential video. However, the emotions in short sequential videos only reflect instantaneous emotions, which may be deliberately guided or hidden. In contrast, long sequential videos can reveal authentic emotions; 2) Previous studies commonly utilize various signals such as facial, speech, and even sensitive biological signals (e.g., electrocardiogram). However, due to the increasing demand for privacy, developing Emotion AI without relying on sensitive signals is becoming important. To address the aforementioned limitations, in this paper, we construct a dataset for Emotion Analysis in Long-sequential and De-identity videos called EALD by collecting and processing the sequences of athletes' post-match interviews. In addition to providing annotations of the overall emotional state of each video, we also provide the Non-Facial Body Language (NFBL) annotations for each player. NFBL is an inner-driven emotional expression and can serve as an identity-free clue to understanding the emotional state. Moreover, we provide a simple but effective baseline for further research. More precisely, we evaluate the Multimodal Large Language Models (MLLMs) with de-identification signals (e.g., visual, speech, and NFBLs) to perform emotion analysis. Our experimental results demonstrate that: 1) MLLMs can achieve comparable, even better performance than the supervised single-modal models, even in a zero-shot scenario; 2) NFBL is an important cue in long sequential emotion analysis. EALD will be available on the open-source platform.

Zhuozhao Hu, Kaishen Yuan, Xin Liu et al.

Facial Emotion Analysis (FEA) plays a crucial role in visual affective computing, aiming to infer a person's emotional state based on facial data. Scientifically, facial expressions (FEs) result from the coordinated movement of facial muscles, which can be decomposed into specific action units (AUs) that provide detailed emotional insights. However, traditional methods often struggle with limited interpretability, constrained generalization and reasoning abilities. Recently, Multimodal Large Language Models (MLLMs) have shown exceptional performance in various visual tasks, while they still face significant challenges in FEA due to the lack of specialized datasets and their inability to capture the intricate relationships between FEs and AUs. To address these issues, we introduce a novel FEA Instruction Dataset that provides accurate and aligned FE and AU descriptions and establishes causal reasoning relationships between them, followed by constructing a new benchmark, FEABench. Moreover, we propose FEALLM, a novel MLLM architecture designed to capture more detailed facial information, enhancing its capability in FEA tasks. Our model demonstrates strong performance on FEABench and impressive generalization capability through zero-shot evaluation on various datasets, including RAF-DB, AffectNet, BP4D, and DISFA, showcasing its robustness and effectiveness in FEA tasks. The dataset and code will be available at https://github.com/953206211/FEALLM.

Licai Sun, Xingxun Jiang, Haoyu Chen et al.

Current facial emotion recognition systems are predominately trained to predict a fixed set of predefined categories or abstract dimensional values. This constrained form of supervision hinders generalization and applicability, as it reduces the rich and nuanced spectrum of emotions into oversimplified labels or scales. In contrast, natural language provides a more flexible, expressive, and interpretable way to represent emotions, offering a much broader source of supervision. Yet, leveraging semantically rich natural language captions as supervisory signals for facial emotion representation learning remains relatively underexplored, primarily due to two key challenges: 1) the lack of large-scale caption datasets with rich emotional semantics, and 2) the absence of effective frameworks tailored to harness such rich supervision. To this end, we introduce EmoCap100K, a large-scale facial emotion caption dataset comprising over 100,000 samples, featuring rich and structured semantic descriptions that capture both global affective states and fine-grained local facial behaviors. Building upon this dataset, we further propose EmoCapCLIP, which incorporates a joint global-local contrastive learning framework enhanced by a cross-modal guided positive mining module. This design facilitates the comprehensive exploitation of multi-level caption information while accommodating semantic similarities between closely related expressions. Extensive evaluations on over 20 benchmarks covering five tasks demonstrate the superior performance of our method, highlighting the promise of learning facial emotion representations from large-scale semantically rich captions. The code and data will be available at https://github.com/sunlicai/EmoCapCLIP.

Yong Li, Menglin Liu, Zhen Cui et al.

Despite the impressive performance of current vision-based facial action unit (AU) detection approaches, they are heavily susceptible to the variations across different domains and the cross-domain AU detection methods are under-explored. In response to this challenge, we propose a decoupled doubly contrastive adaptation (D$^2$CA) approach to learn a purified AU representation that is semantically aligned for the source and target domains. Specifically, we decompose latent representations into AU-relevant and AU-irrelevant components, with the objective of exclusively facilitating adaptation within the AU-relevant subspace. To achieve the feature decoupling, D$^2$CA is trained to disentangle AU and domain factors by assessing the quality of synthesized faces in cross-domain scenarios when either AU or domain attributes are modified. To further strengthen feature decoupling, particularly in scenarios with limited AU data diversity, D$^2$CA employs a doubly contrastive learning mechanism comprising image and feature-level contrastive learning to ensure the quality of synthesized faces and mitigate feature ambiguities. This new framework leads to an automatically learned, dedicated separation of AU-relevant and domain-relevant factors, and it enables intuitive, scale-specific control of the cross-domain facial image synthesis. Extensive experiments demonstrate the efficacy of D$^2$CA in successfully decoupling AU and domain factors, yielding visually pleasing cross-domain synthesized facial images. Meanwhile, D$^2$CA consistently outperforms state-of-the-art cross-domain AU detection approaches, achieving an average F1 score improvement of 6\%-14\% across various cross-domain scenarios.

Yong Wang, Cheng Lu, Hailun Lian et al.

Swin-Transformer has demonstrated remarkable success in computer vision by leveraging its hierarchical feature representation based on Transformer. In speech signals, emotional information is distributed across different scales of speech features, e.\,g., word, phrase, and utterance. Drawing above inspiration, this paper presents a hierarchical speech Transformer with shifted windows to aggregate multi-scale emotion features for speech emotion recognition (SER), called Speech Swin-Transformer. Specifically, we first divide the speech spectrogram into segment-level patches in the time domain, composed of multiple frame patches. These segment-level patches are then encoded using a stack of Swin blocks, in which a local window Transformer is utilized to explore local inter-frame emotional information across frame patches of each segment patch. After that, we also design a shifted window Transformer to compensate for patch correlations near the boundaries of segment patches. Finally, we employ a patch merging operation to aggregate segment-level emotional features for hierarchical speech representation by expanding the receptive field of Transformer from frame-level to segment-level. Experimental results demonstrate that our proposed Speech Swin-Transformer outperforms the state-of-the-art methods.

Cheng Lu, Yuan Zong, Hailun Lian et al.

In speaker-independent speech emotion recognition, the training and testing samples are collected from diverse speakers, leading to a multi-domain shift challenge across the feature distributions of data from different speakers. Consequently, when the trained model is confronted with data from new speakers, its performance tends to degrade. To address the issue, we propose a Dynamic Joint Distribution Adaptation (DJDA) method under the framework of multi-source domain adaptation. DJDA firstly utilizes joint distribution adaptation (JDA), involving marginal distribution adaptation (MDA) and conditional distribution adaptation (CDA), to more precisely measure the multi-domain distribution shifts caused by different speakers. This helps eliminate speaker bias in emotion features, allowing for learning discriminative and speaker-invariant speech emotion features from coarse-level to fine-level. Furthermore, we quantify the adaptation contributions of MDA and CDA within JDA by using a dynamic balance factor based on $\mathcal{A}$-Distance, promoting to effectively handle the unknown distributions encountered in data from new speakers. Experimental results demonstrate the superior performance of our DJDA as compared to other state-of-the-art (SOTA) methods.

Xingxun Jiang, Yuan Zong, Wenming Zheng et al.

Cross-Database Micro-Expression Recognition (CDMER) aims to develop the Micro-Expression Recognition (MER) methods with strong domain adaptability, i.e., the ability to recognize the Micro-Expressions (MEs) of different subjects captured by different imaging devices in different scenes. The development of CDMER is faced with two key problems: 1) the severe feature distribution gap between the source and target databases; 2) the feature representation bottleneck of ME such local and subtle facial expressions. To solve these problems, this paper proposes a novel Transfer Group Sparse Regression method, namely TGSR, which aims to 1) optimize the measurement and better alleviate the difference between the source and target databases, and 2) highlight the valid facial regions to enhance extracted features, by the operation of selecting the group features from the raw face feature, where each region is associated with a group of raw face feature, i.e., the salient facial region selection. Compared with previous transfer group sparse methods, our proposed TGSR has the ability to select the salient facial regions, which is effective in alleviating the aforementioned problems for better performance and reducing the computational cost at the same time. We use two public ME databases, i.e., CASME II and SMIC, to evaluate our proposed TGSR method. Experimental results show that our proposed TGSR learns the discriminative and explicable regions, and outperforms most state-of-the-art subspace-learning-based domain-adaptive methods for CDMER.

Jiateng Liu, Wenming Zheng, Yuan Zong

Correctly perceiving micro-expression is difficult since micro-expression is an involuntary, repressed, and subtle facial expression, and efficiently revealing the subtle movement changes and capturing the significant segments in a micro-expression sequence is the key to micro-expression recognition (MER). To handle the crucial issue, in this paper, we firstly propose a dynamic segmented sparse imaging module (DSSI) to compute dynamic images as local-global spatiotemporal descriptors under a unique sampling protocol, which reveals the subtle movement changes visually in an efficient way. Secondly, a segmented movement-attending spatiotemporal network (SMA-STN) is proposed to further unveil imperceptible small movement changes, which utilizes a spatiotemporal movement-attending module (STMA) to capture long-distance spatial relation for facial expression and weigh temporal segments. Besides, a deviation enhancement loss (DE-Loss) is embedded in the SMA-STN to enhance the robustness of SMA-STN to subtle movement changes in feature level. Extensive experiments on three widely used benchmarks, i.e., CASME II, SAMM, and SHIC, show that the proposed SMA-STN achieves better MER performance than other state-of-the-art methods, which proves that the proposed method is effective to handle the challenging MER problem.

Yuan Fang, Chunyan Xu, Zhen Cui et al.

Point clouds are unstructured and unordered in the embedded 3D space. In order to produce consistent responses under different permutation layouts, most existing methods aggregate local spatial points through maximum or summation operation. But such an aggregation essentially belongs to the isotropic filtering on all operated points therein, which tends to lose the information of geometric structures. In this paper, we propose a spatial transformer point convolution (STPC) method to achieve anisotropic convolution filtering on point clouds. To capture and represent implicit geometric structures, we specifically introduce spatial direction dictionary to learn those latent geometric components. To better encode unordered neighbor points, we design sparse deformer to transform them into the canonical ordered dictionary space by using direction dictionary learning. In the transformed space, the standard image-like convolution can be leveraged to generate anisotropic filtering, which is more robust to express those finer variances of local regions. Dictionary learning and encoding processes are encapsulated into a network module and jointly learnt in an end-to-end manner. Extensive experiments on several public datasets (including S3DIS, Semantic3D, SemanticKITTI) demonstrate the effectiveness of our proposed method in point clouds semantic segmentation task.

Xingxun Jiang, Yuan Zong, Wenming Zheng et al.

Recently, facial expression recognition (FER) in the wild has gained a lot of researchers' attention because it is a valuable topic to enable the FER techniques to move from the laboratory to the real applications. In this paper, we focus on this challenging but interesting topic and make contributions from three aspects. First, we present a new large-scale 'in-the-wild' dynamic facial expression database, DFEW (Dynamic Facial Expression in the Wild), consisting of over 16,000 video clips from thousands of movies. These video clips contain various challenging interferences in practical scenarios such as extreme illumination, occlusions, and capricious pose changes. Second, we propose a novel method called Expression-Clustered Spatiotemporal Feature Learning (EC-STFL) framework to deal with dynamic FER in the wild. Third, we conduct extensive benchmark experiments on DFEW using a lot of spatiotemporal deep feature learning methods as well as our proposed EC-STFL. Experimental results show that DFEW is a well-designed and challenging database, and the proposed EC-STFL can promisingly improve the performance of existing spatiotemporal deep neural networks in coping with the problem of dynamic FER in the wild. Our DFEW database is publicly available and can be freely downloaded from https://dfew-dataset.github.io/.

Yuan Zong, Tong Zhang, Wenming Zheng et al.

Cross-database micro-expression recognition (CDMER) is one of recently emerging and interesting problem in micro-expression analysis. CDMER is more challenging than the conventional micro-expression recognition (MER), because the training and testing samples in CDMER come from different micro-expression databases, resulting in the inconsistency of the feature distributions between the training and testing sets. In this paper, we contribute to this topic from three aspects. First, we establish a CDMER experimental evaluation protocol aiming to allow the researchers to conveniently work on this topic and provide a standard platform for evaluating their proposed methods. Second, we conduct benchmark experiments by using NINE state-of-the-art domain adaptation (DA) methods and SIX popular spatiotemporal descriptors for respectively investigating CDMER problem from two different perspectives. Third, we propose a novel DA method called region selective transfer regression (RSTR) to deal with the CDMER task. Our RSTR takes advantage of one important cue for recognizing micro-expressions, i.e., the different contributions of the facial local regions in MER. The overall superior performance of RSTR demonstrates that taking into consideration the important cues benefiting MER, e.g., the facial local region information, contributes to develop effective DA methods for dealing with CDMER problem.

Keyu Yan, Wenming Zheng, Tong Zhang et al.

Cross-database non-frontal expression recognition is a very meaningful but rather difficult subject in the fields of computer vision and affect computing. In this paper, we proposed a novel transductive deep transfer learning architecture based on widely used VGGface16-Net for this problem. In this framework, the VGGface16-Net is used to jointly learn an common optimal nonlinear discriminative features from the non-frontal facial expression samples between the source and target databases and then we design a novel transductive transfer layer to deal with the cross-database non-frontal facial expression classification task. In order to validate the performance of the proposed transductive deep transfer learning networks, we present extensive crossdatabase experiments on two famous available facial expression databases, namely the BU-3DEF and the Multi-PIE database. The final experimental results show that our transductive deep transfer network outperforms the state-of-the-art cross-database facial expression recognition methods.

Yuan Zong, Xiaohua Huang, Wenming Zheng et al.

In this paper, we investigate the cross-database micro-expression recognition problem, where the training and testing samples are from two different micro-expression databases. Under this setting, the training and testing samples would have different feature distributions and hence the performance of most existing micro-expression recognition methods may decrease greatly. To solve this problem, we propose a simple yet effective method called Target Sample Re-Generator (TSRG) in this paper. By using TSRG, we are able to re-generate the samples from target micro-expression database and the re-generated target samples would share same or similar feature distributions with the original source samples. For this reason, we can then use the classifier learned based on the labeled source samples to accurately predict the micro-expression categories of the unlabeled target samples. To evaluate the performance of the proposed TSRG method, extensive cross-database micro-expression recognition experiments designed based on SMIC and CASME II databases are conducted. Compared with recent state-of-the-art cross-database emotion recognition methods, the proposed TSRG achieves more promising results.

Tong Zhang, Wenming Zheng, Zhen Cui et al.

Emotion analysis is a crucial problem to endow artifact machines with real intelligence in many large potential applications. As external appearances of human emotions, electroencephalogram (EEG) signals and video face signals are widely used to track and analyze human's affective information. According to their common characteristics of spatial-temporal volumes, in this paper we propose a novel deep learning framework named spatial-temporal recurrent neural network (STRNN) to unify the learning of two different signal sources into a spatial-temporal dependency model. In STRNN, to capture those spatially cooccurrent variations of human emotions, a multi-directional recurrent neural network (RNN) layer is employed to capture longrange contextual cues by traversing the spatial region of each time slice from multiple angles. Then a bi-directional temporal RNN layer is further used to learn discriminative temporal dependencies from the sequences concatenating spatial features of each time slice produced from the spatial RNN layer. To further select those salient regions of emotion representation, we impose sparse projection onto those hidden states of spatial and temporal domains, which actually also increases the model discriminant ability because of this global consideration. Consequently, such a two-layer RNN model builds spatial dependencies as well as temporal dependencies of the input signals. Experimental results on the public emotion datasets of EEG and facial expression demonstrate the proposed STRNN method is more competitive over those state-of-the-art methods.