Multi-modal entity alignment aims to identify equivalent entities between two different multi-modal knowledge graphs, which consist of structural triples and images associated with entities. Most previous works focus on how to utilize and encode information from different modalities, while it is not trivial to leverage multi-modal knowledge in entity alignment because of the modality heterogeneity. In this paper, we propose MCLEA, a Multi-modal Contrastive Learning based Entity Alignment model, to obtain effective joint representations for multi-modal entity alignment. Different from previous works, MCLEA considers task-oriented modality and models the inter-modal relationships for each entity representation. In particular, MCLEA firstly learns multiple individual representations from multiple modalities, and then performs contrastive learning to jointly model intra-modal and inter-modal interactions. Extensive experimental results show that MCLEA outperforms state-of-the-art baselines on public datasets under both supervised and unsupervised settings.
In this paper, we present an end-to-end approach to generate high-resolution person images conditioned on texts only. State-of-the-art text-to-image generation models are mainly designed for center-object generation, e.g., flowers and birds. Unlike center-placed objects with similar shapes and orientation, person image generation is a more challenging task, for which we observe the followings: 1) the generated images for the same person exhibit visual details with identity-consistency, e.g., identity-related textures/clothes/shoes across the images, and 2) those images should be discriminant for being robust against the inter-person variations caused by visual ambiguities. To address the above challenges, we develop an effective generative model to produce person images with two novel mechanisms. In particular, our first mechanism (called T-Person-GAN-ID) is to integrate the one-stream generator with an identity-preserving network such that the representations of generated data are regularized in their feature space to ensure the identity-consistency. The second mechanism (called T-Person-GAN-ID-MM) is based on the manifold mix-up to produce mixed images via the linear interpolation across generated images from different manifold identities, and we further enforce such interpolated images to be linearly classified in the feature space. This amounts to learning a linear classification boundary that can perfectly separate images from two identities. Our proposed method is empirically validated to achieve a remarkable improvement in text-to-person image generation. Our architecture is orthogonal to StackGAN++ , and focuses on person image generation, with all of them together to enrich the spectrum of GANs for the image generation task. Codes are available on \url{https://github.com/linwu-github/Person-Image-Generation.git}.
Temporal action localization plays an important role in video analysis, which aims to localize and classify actions in untrimmed videos. The previous methods often predict actions on a feature space of a single-temporal scale. However, the temporal features of a low-level scale lack enough semantics for action classification while a high-level scale cannot provide rich details of the action boundaries. To address this issue, we propose to predict actions on a feature space of multi-temporal scales. Specifically, we use refined feature pyramids of different scales to pass semantics from high-level scales to low-level scales. Besides, to establish the long temporal scale of the entire video, we use a spatial-temporal transformer encoder to capture the long-range dependencies of video frames. Then the refined features with long-range dependencies are fed into a classifier for the coarse action prediction. Finally, to further improve the prediction accuracy, we propose to use a frame-level self attention module to refine the classification and boundaries of each action instance. Extensive experiments show that the proposed method can outperform state-of-the-art approaches on the THUMOS14 dataset and achieves comparable performance on the ActivityNet1.3 dataset. Compared with A2Net (TIP20, Avg\{0.3:0.7\}), Sub-Action (CSVT2022, Avg\{0.1:0.5\}), and AFSD (CVPR21, Avg\{0.3:0.7\}) on the THUMOS14 dataset, the proposed method can achieve improvements of 12.6\%, 17.4\% and 2.2\%, respectively
In this paper, we present our solutions for the Multimodal Sentiment Analysis Challenge (MuSe) 2022, which includes MuSe-Humor, MuSe-Reaction and MuSe-Stress Sub-challenges. The MuSe 2022 focuses on humor detection, emotional reactions and multimodal emotional stress utilizing different modalities and data sets. In our work, different kinds of multimodal features are extracted, including acoustic, visual, text and biological features. These features are fused by TEMMA and GRU with self-attention mechanism frameworks. In this paper, 1) several new audio features, facial expression features and paragraph-level text embeddings are extracted for accuracy improvement. 2) we substantially improve the accuracy and reliability of multimodal sentiment prediction by mining and blending the multimodal features. 3) effective data augmentation strategies are applied in model training to alleviate the problem of sample imbalance and prevent the model from learning biased subject characters. For the MuSe-Humor sub-challenge, our model obtains the AUC score of 0.8932. For the MuSe-Reaction sub-challenge, the Pearson's Correlations Coefficient of our approach on the test set is 0.3879, which outperforms all other participants. For the MuSe-Stress sub-challenge, our approach outperforms the baseline in both arousal and valence on the test dataset, reaching a final combined result of 0.5151.
Recommender systems are prone to be misled by biases in the data. Models trained with biased data fail to capture the real interests of users, thus it is critical to alleviate the impact of bias to achieve unbiased recommendation. In this work, we focus on an essential bias in micro-video recommendation, duration bias. Specifically, existing micro-video recommender systems usually consider watch time as the most critical metric, which measures how long a user watches a video. Since videos with longer duration tend to have longer watch time, there exists a kind of duration bias, making longer videos tend to be recommended more against short videos. In this paper, we empirically show that commonly-used metrics are vulnerable to duration bias, making them NOT suitable for evaluating micro-video recommendation. To address it, we further propose an unbiased evaluation metric, called WTG (short for Watch Time Gain). Empirical results reveal that WTG can alleviate duration bias and better measure recommendation performance. Moreover, we design a simple yet effective model named DVR (short for Debiased Video Recommendation) that can provide unbiased recommendation of micro-videos with varying duration, and learn unbiased user preferences via adversarial learning. Extensive experiments based on two real-world datasets demonstrate that DVR successfully eliminates duration bias and significantly improves recommendation performance with over 30% relative progress. Codes and datasets are released at https://github.com/tsinghua-fib-lab/WTG-DVR.
Human leukocyte antigen (HLA) is an important molecule family in the field of human immunity, which recognizes foreign threats and triggers immune responses by presenting peptides to T cells. In recent years, the synthesis of tumor vaccines to induce specific immune responses has become the forefront of cancer treatment. Computationally modeling the binding patterns between peptide and HLA can greatly accelerate the development of tumor vaccines. However, most of the prediction methods performance is very limited and they cannot fully take advantage of the analysis of existing biological knowledge as the basis of modeling. In this paper, we propose TripHLApan, a novel pan-specific prediction model, for HLA molecular peptide binding prediction. TripHLApan exhibits powerful prediction ability by integrating triple coding matrix, BiGRU + Attention models, and transfer learning strategy. The comprehensive evaluations demonstrate the effectiveness of TripHLApan in predicting HLA-I and HLA-II peptide binding in different test environments. The predictive power of HLA-I is further demonstrated in the latest data set. In addition, we show that TripHLApan has strong binding reconstitution ability in the samples of a melanoma patient. In conclusion, TripHLApan is a powerful tool for predicting the binding of HLA-I and HLA-II molecular peptides for the synthesis of tumor vaccines.
Uncalibrated photometric stereo is proposed to estimate the detailed surface normal from images under varying and unknown lightings. Recently, deep learning brings powerful data priors to this underdetermined problem. This paper presents a new method for deep uncalibrated photometric stereo, which efficiently utilizes the inter-image representation to guide the normal estimation. Previous methods use optimization-based neural inverse rendering or a single size-independent pooling layer to deal with multiple inputs, which are inefficient for utilizing information among input images. Given multi-images under different lighting, we consider the intra-image and inter-image variations highly correlated. Motivated by the correlated variations, we designed an inter-intra image feature fusion module to introduce the inter-image representation into the per-image feature extraction. The extra representation is used to guide the per-image feature extraction and eliminate the ambiguity in normal estimation. We demonstrate the effect of our design on a wide range of samples, especially on dark materials. Our method produces significantly better results than the state-of-the-art methods on both synthetic and real data.
Tracking position and orientation independently affords more agile maneuver for over-actuated multirotor Unmanned Aerial Vehicles (UAVs) while introducing undesired downwash effects; downwash flows generated by thrust generators may counteract others due to close proximity, which significantly threatens the stability of the platform. The complexity of modeling aerodynamic airflow challenges control algorithms from properly compensating for such a side effect. Leveraging the input redundancies in over-actuated UAVs, we tackle this issue with a novel control allocation framework that considers downwash effects and explores the entire allocation space for an optimal solution. This optimal solution avoids downwash effects while providing high thrust efficiency within the hardware constraints. To the best of our knowledge, ours is the first formal derivation to investigate the downwash effects on over-actuated UAVs. We verify our framework on different hardware configurations in both simulation and experiment.
Cloth-changing person reidentification (ReID) is a newly emerging research topic that aims to retrieve pedestrians whose clothes are changed. Since the human appearance with different clothes exhibits large variations, it is very difficult for existing approaches to extract discriminative and robust feature representations. Current works mainly focus on body shape or contour sketches, but the human semantic information and the potential consistency of pedestrian features before and after changing clothes are not fully explored or are ignored. To solve these issues, in this work, a novel semantic-aware attention and visual shielding network for cloth-changing person ReID (abbreviated as SAVS) is proposed where the key idea is to shield clues related to the appearance of clothes and only focus on visual semantic information that is not sensitive to view/posture changes. Specifically, a visual semantic encoder is first employed to locate the human body and clothing regions based on human semantic segmentation information. Then, a human semantic attention module (HSA) is proposed to highlight the human semantic information and reweight the visual feature map. In addition, a visual clothes shielding module (VCS) is also designed to extract a more robust feature representation for the cloth-changing task by covering the clothing regions and focusing the model on the visual semantic information unrelated to the clothes. Most importantly, these two modules are jointly explored in an end-to-end unified framework. Extensive experiments demonstrate that the proposed method can significantly outperform state-of-the-art methods, and more robust features can be extracted for cloth-changing persons. Compared with FSAM (published in CVPR 2021), this method can achieve improvements of 32.7% (16.5%) and 14.9% (-) on the LTCC and PRCC datasets in terms of mAP (rank-1), respectively.