With the rapid prevalence and explosive development of MOBA esports (Multiplayer Online Battle Arena electronic sports), many research efforts have been devoted to automatically predicting the game results (win predictions). While this task has great potential in various applications such as esports live streaming and game commentator AI systems, previous studies suffer from two major limitations: 1) insufficient real-time input features and high-quality training data; 2) non-interpretable inference processes of the black-box prediction models. To mitigate these issues, we collect and release a large-scale dataset that contains real-time game records with rich input features of the popular MOBA game Honor of Kings. For interpretable predictions, we propose a Two-Stage Spatial-Temporal Network (TSSTN) that can not only provide accurate real-time win predictions but also attribute the ultimate prediction results to the contributions of different features for interpretability. Experiment results and applications in real-world live streaming scenarios show that the proposed TSSTN model is effective both in prediction accuracy and interpretability.
Lane detection is one of the most important tasks in self-driving. Due to various complex scenarios (e.g., severe occlusion, ambiguous lanes, and etc.) and the sparse supervisory signals inherent in lane annotations, lane detection task is still challenging. Thus, it is difficult for ordinary convolutional neural network (CNN) trained in general scenes to catch subtle lane feature from raw image. In this paper, we present a novel module named REcurrent Feature-Shift Aggregator (RESA) to enrich lane feature after preliminary feature extraction with an ordinary CNN. RESA takes advantage of strong shape priors of lanes and captures spatial relationships of pixels across rows and columns. It shifts sliced feature map recurrently in vertical and horizontal directions and enables each pixel to gather global information. With the help of slice-by-slice information propagation, RESA can conjecture lanes accurately in challenging scenarios with weak appearance clues. Moreover, we also propose a Bilateral Up-Sampling Decoder which combines coarse grained feature and fine detailed feature in up-sampling stage, and it can recover low-resolution feature map into pixel-wise prediction meticulously. Our method achieves state-of-the-art results on two popular lane detection benchmarks (CULane and Tusimple). The code will be released publicly available.
With the rise of deep learning methods, person Re-Identification (ReID) performance has been improved tremendously in many public datasets. However, most public ReID datasets are collected in a short time window in which persons' appearance rarely changes. In real-world applications such as in a shopping mall, the same person's clothing may change, and different persons may wearing similar clothes. All these cases can result in an inconsistent ReID performance, revealing a critical problem that current ReID models heavily rely on person's apparels. Therefore, it is critical to learn an apparel-invariant person representation under cases like cloth changing or several persons wearing similar clothes. In this work, we tackle this problem from the viewpoint of invariant feature representation learning. The main contributions of this work are as follows. (1) We propose the semi-supervised Apparel-invariant Feature Learning (AIFL) framework to learn an apparel-invariant pedestrian representation using images of the same person wearing different clothes. (2) To obtain images of the same person wearing different clothes, we propose an unsupervised apparel-simulation GAN (AS-GAN) to synthesize cloth changing images according to the target cloth embedding. It's worth noting that the images used in ReID tasks were cropped from real-world low-quality CCTV videos, making it more challenging to synthesize cloth changing images. We conduct extensive experiments on several datasets comparing with several baselines. Experimental results demonstrate that our proposal can improve the ReID performance of the baseline models.
Caricature is an artistic drawing created to abstract or exaggerate facial features of a person. Rendering visually pleasing caricatures is a difficult task that requires professional skills, and thus it is of great interest to design a method to automatically generate such drawings. To deal with large shape changes, we propose an algorithm based on a semantic shape transform to produce diverse and plausible shape exaggerations. Specifically, we predict pixel-wise semantic correspondences and perform image warping on the input photo to achieve dense shape transformation. We show that the proposed framework is able to render visually pleasing shape exaggerations while maintaining their facial structures. In addition, our model allows users to manipulate the shape via the semantic map. We demonstrate the effectiveness of our approach on a large photograph-caricature benchmark dataset with comparisons to the state-of-the-art methods.
Manipulating visual attributes of images through human-written text is a very challenging task. On the one hand, models have to learn the manipulation without the ground truth of the desired output. On the other hand, models have to deal with the inherent ambiguity of natural language. Previous research usually requires either the user to describe all the characteristics of the desired image or to use richly-annotated image captioning datasets. In this work, we propose a novel unsupervised approach, based on image-to-image translation, that alters the attributes of a given image through a command-like sentence such as "change the hair color to black". Contrarily to state-of-the-art approaches, our model does not require a human-annotated dataset nor a textual description of all the attributes of the desired image, but only those that have to be modified. Our proposed model disentangles the image content from the visual attributes, and it learns to modify the latter using the textual description, before generating a new image from the content and the modified attribute representation. Because text might be inherently ambiguous (blond hair may refer to different shadows of blond, e.g. golden, icy, sandy), our method generates multiple stochastic versions of the same translation. Experiments show that the proposed model achieves promising performances on two large-scale public datasets: CelebA and CUB. We believe our approach will pave the way to new avenues of research combining textual and speech commands with visual attributes.
How to learn a stable model under agnostic distribution shift between training and testing datasets is an essential problem in machine learning tasks. The agnostic distribution shift caused by data generation bias can lead to model misspecification and unstable performance across different test datasets. Most of the recently proposed methods are causality-based sample reweighting methods, whose performance is affected by sample size. Moreover, these works are restricted to linear models, not to deep-learning based nonlinear models. In this work, we propose a novel Causality-based Feature Rectification (CFR) method to address the model misspecification problem under agnostic distribution shift by using a weight matrix to rectify features. Our proposal based on the fact that the causality between stable features and the ground truth is consistent under agnostic distribution shift, but is partly omitted and statistically correlated with other features. We propose the feature rectification weight matrix to reconstruct the omitted causality by using other features as proxy variables. We further propose an algorithm that jointly optimizes the weight matrix and the regressor (or classifier). Our proposal can not only improve the stability of linear models, but also deep-learning based models. Extensive experiments on both synthetic and real-world datasets demonstrate that our proposal outperforms previous state-of-the-art stable learning methods. The code will be released later on.
Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e., dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within this framework, the forward and backward networks are able to iteratively promote or demote each other's generated instances by comparing the real and synthetic data distributions. We also develop a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process. Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem.
We propose a new end-to-end model that treats AMR parsing as a series of dual decisions on the input sequence and the incrementally constructed graph. At each time step, our model performs multiple rounds of attention, reasoning, and composition that aim to answer two critical questions: (1) which part of the input \textit{sequence} to abstract; and (2) where in the output \textit{graph} to construct the new concept. We show that the answers to these two questions are mutually causalities. We design a model based on iterative inference that helps achieve better answers in both perspectives, leading to greatly improved parsing accuracy. Our experimental results significantly outperform all previously reported \textsc{Smatch} scores by large margins. Remarkably, without the help of any large-scale pre-trained language model (e.g., BERT), our model already surpasses previous state-of-the-art using BERT. With the help of BERT, we can push the state-of-the-art results to 80.2\% on LDC2017T10 (AMR 2.0) and 75.4\% on LDC2014T12 (AMR 1.0).