This paper studies how to flexibly integrate reconstructed 3D models into practical 3D modeling pipelines such as 3D scene creation and rendering. Due to the technical difficulty, one can only obtain rough 3D models (R3DMs) for most real objects using existing 3D reconstruction techniques. As a result, physically-based rendering (PBR) would render low-quality images or videos for scenes that are constructed by R3DMs. One promising solution would be representing real-world objects as Neural Fields such as NeRFs, which are able to generate photo-realistic renderings of an object under desired viewpoints. However, a drawback is that the synthesized views through Neural Fields Rendering (NFR) cannot reflect the simulated lighting details on R3DMs in PBR pipelines, especially when object interactions in the 3D scene creation cause local shadows. To solve this dilemma, we propose a lighting transfer network (LighTNet) to bridge NFR and PBR, such that they can benefit from each other. LighTNet reasons about a simplified image composition model, remedies the uneven surface issue caused by R3DMs, and is empowered by several perceptual-motivated constraints and a new Lab angle loss which enhances the contrast between lighting strength and colors. Comparisons demonstrate that LighTNet is superior in synthesizing impressive lighting, and is promising in pushing NFR further in practical 3D modeling workflows.

Learning high-quality sentence representations is a fundamental problem of natural language processing which could benefit a wide range of downstream tasks.Though the BERT-like pretrained language models have achieved great success, using their sentence representations directly often results in poor performance on the semantic textual similarity task.Recently, several contrastive learning methods have been proposed for learning sentence representations and have shown promising results.However, most of them focus on the constitution of positive and negative representation pairs and pay little attention to the training objective like NT-Xent, which is not sufficient enough to acquire the discriminating power and is unable to model the partial order of semantics between sentences.So in this paper, we propose a new method ArcCSE, with training objectives designed to enhance the pairwise discriminative power and model the entailment relation of triplet sentences.We conduct extensive experiments which demonstrate that our approach outperforms the previous state-of-the-art on diverse sentence related tasks, including STS and SentEval.

Due to the large-scale users and items, industrial recommender systems usually consist of two stages, the matching stage and the ranking stage. The matching stage is responsible for retrieving a small fraction of relevant items from the large-scale item pool which are further selected by the ranking stage. Most of the existing deep learning-based matching models focus on the problem of modeling user interest representation by using inner product between user representation and item representation to obtain the user-to-item relevance. However, the item-to-item relevance between user interacted item and target item is not considered in the deep matching models which is computationally prohibitive for large-scale applications. In this paper, we propose a unified deep matching framework called UDM for the matching stage to mitigate this issue. UDM can model the user-to-item relevance and item-to-item relevance simultaneously with the help of an interest extraction module and interest interaction module, respectively. Specifically, the interest extraction module is used as the main network to extract users' multiple interests with multiple vectors based on users' behavior sequences, while the interest interaction module is used as an auxiliary network to supervise the learning of the interest extraction module, which can model the interaction between user interacted items and target item. In the experiments conducted on two public datasets and a large-scale industrial dataset, UDM achieves consistent improvements over state-of-the-art models. Moreover, UDM has been deployed in the operational system of Alibaba. Online A/B testing results further reveal the effectiveness of UDM. To the best of our knowledge, UDM is the first deep matching framework which combines the user-to-item relevance modeling and item-to-item relevance modeling in the same model.

Neural Radiance Fields (NeRF) [22] have emerged as a potent paradigm for representing scenes and synthesizing photo-realistic images. A main limitation of conventional NeRFs is that they often fail to produce high-quality renderings under novel viewpoints that are significantly different from the training viewpoints. In this paper, instead of ex-ploiting few-shot image synthesis, we study the novel view extrapolation setting that (1) the training images can well describe an object, and (2) there is a notable discrepancy between the training and test viewpoints' distributions. We present RapNeRF (RAy Priors) as a solution. Our insight is that the inherent appearances of a 3D surface's arbitrary visible projections should be consistent. We thus propose a random ray casting policy that allows training unseen views using seen views. Furthermore, we show that a ray atlas pre-computed from the observed rays' viewing directions could further enhance the rendering quality for ex-trapolated views. A main limitation is that RapNeRF would remove the strong view-dependent effects because it lever-ages the multi-view consistency property.

Recommender system usually faces popularity bias. From the popularity distribution shift perspective, the normal paradigm trained on exposed items (most are hot items) identifies that recommending popular items more frequently can achieve lower loss, thus injecting popularity information into item property embedding, e.g., id embedding. From the long-tail distribution shift perspective, the sparse interactions of long-tail items lead to insufficient learning of them. The resultant distribution discrepancy between hot and long-tail items would not only inherit the bias, but also amplify the bias. Existing work addresses this issue with inverse propensity scoring (IPS) or causal embeddings. However, we argue that not all popularity biases mean bad effects, i.e., some items show higher popularity due to better quality or conform to current trends, which deserve more recommendations. Blindly seeking unbiased learning may inhibit high-quality or fashionable items. To make better use of the popularity bias, we propose a co-training disentangled domain adaptation network (CD$^2$AN), which can co-train both biased and unbiased models. Specifically, for popularity distribution shift, CD$^2$AN disentangles item property representation and popularity representation from item property embedding. For long-tail distribution shift, we introduce additional unexposed items (most are long-tail items) to align the distribution of hot and long-tail item property representations. Further, from the instances perspective, we carefully design the item similarity regularization to learn comprehensive item representation, which encourages item pairs with more effective co-occurrences patterns to have more similar item property representations. Based on offline evaluations and online A/B tests, we show that CD$^2$AN outperforms the existing debiased solutions. Currently, CD$^2$AN has been successfully deployed at Mobile Taobao App and handling major online traffic.

Adapting semantic segmentation models to new domains is an important but challenging problem. Recently enlightening progress has been made, but the performance of existing methods is unsatisfactory on real datasets where the new target domain comprises of heterogeneous sub-domains (e.g. diverse weather characteristics). We point out that carefully reasoning about the multiple modalities in the target domain can improve the robustness of adaptation models. To this end, we propose a condition-guided adaptation framework that is empowered by a special attentive progressive adversarial training (APAT) mechanism and a novel self-training policy. The APAT strategy progressively performs condition-specific alignment and attentive global feature matching. The new self-training scheme exploits the adversarial ambivalences of easy and hard adaptation regions and the correlations among target sub-domains effectively. We evaluate our method (DCAA) on various adaptation scenarios where the target images vary in weather conditions. The comparisons against baselines and the state-of-the-art approaches demonstrate the superiority of DCAA over the competitors.

Locating and classifying clothes, usually referred to as clothing detection, is a fundamental task in fashion analysis. Motivated by the strong structural characteristics of clothes, we pursue a detection method enhanced by clothing keypoints, which is a compact and effective representation of structures. To incorporate the keypoint cues into clothing detection, we design a simple yet effective Keypoint-Guided clothing Detector, named KGDet. Such a detector can fully utilize information provided by keypoints with the following two aspects: i) integrating local features around keypoints to benefit both classification and regression; ii) generating accurate bounding boxes from keypoints. To effectively incorporate local features , two alternative modules are proposed. One is a multi-column keypoint-encoding-based feature aggregation module; the other is a keypoint-selection-based feature aggregation module. With either of the above modules as a bridge, a cascade strategy is introduced to refine detection performance progressively. Thanks to the keypoints, our KGDet obtains superior performance on the DeepFashion2 dataset and the FLD dataset with high efficiency.

Recognition and reconstruction of residential floor plan drawings are important and challenging in design, decoration, and architectural remodeling fields. An automatic framework is provided that accurately recognizes the structure, type, and size of the room, and outputs vectorized 3D reconstruction results. Deep segmentation and detection neural networks are utilized to extract room structural information. Key points detection network and cluster analysis are utilized to calculate scales of rooms. The vectorization of room information is processed through an iterative optimization-based method. The system significantly increases accuracy and generalization ability, compared with existing methods. It outperforms other systems in floor plan segmentation and vectorization process, especially inclined wall detection.

We study a very challenging task, human image completion, which tries to recover the human body part with a reasonable human shape from the corrupted region. Since each human body part is unique, it is infeasible to restore the missing part by borrowing textures from other visible regions. Thus, we propose two types of learned priors to compensate for the damaged region. One is a structure prior, it uses a human parsing map to represent the human body structure. The other is a structure-texture correlation prior. It learns a structure and a texture memory bank, which encodes the common body structures and texture patterns, respectively. With the aid of these memory banks, the model could utilize the visible pattern to query and fetch a similar structure and texture pattern to introduce additional reasonable structures and textures for the corrupted region. Besides, since multiple potential human shapes are underlying the corrupted region, we propose multi-scale structure discriminators to further restore a plausible topological structure. Experiments on various large-scale benchmarks demonstrate the effectiveness of our proposed method.

We introduce 3D-FRONT (3D Furnished Rooms with layOuts and semaNTics), a new, large-scale, and comprehensive repository of synthetic indoor scenes highlighted by professionally designed layouts and a large number of rooms populated by high-quality textured 3D models with style compatibility. From layout semantics down to texture details of individual objects, our dataset is freely available to the academic community and beyond. Currently, 3D-FRONT contains 6,813 CAD houses, where 18,968 rooms diversely furnished by 3D objects, far surpassing all publicly available scene datasets. The 13,151 furniture objects all come with high-quality textures. While the floorplans and layout designs (i.e., furniture arrangements) are directly sourced from professional creations, the interior designs in terms of furniture styles, color, and textures have been carefully curated based on a recommender system we develop to attain consistent styles as expert designs. Furthermore, we release Trescope, a light-weight rendering tool, to support benchmark rendering of 2D images and annotations from 3D-FRONT. We demonstrate two applications, interior scene synthesis and texture synthesis, that are especially tailored to the strengths of our new dataset.

In this work, we tackle the problem of single image-based 3D shape retrieval (IBSR), where we seek to find the most matched shape of a given single 2D image from a shape repository. Most of the existing works learn to embed 2D images and 3D shapes into a common feature space and perform metric learning using a triplet loss. Inspired by the great success in recent contrastive learning works on self-supervised representation learning, we propose a novel IBSR pipeline leveraging contrastive learning. We note that adopting such cross-modal contrastive learning between 2D images and 3D shapes into IBSR tasks is non-trivial and challenging: contrastive learning requires very strong data augmentation in constructed positive pairs to learn the feature invariance, whereas traditional metric learning works do not have this requirement. Moreover, object shape and appearance are entangled in 2D query images, thus making the learning task more difficult than contrasting single-modal data. To mitigate the challenges, we propose to use multi-view grayscale rendered images from the 3D shapes as a shape representation. We then introduce a strong data augmentation technique based on color transfer, which can significantly but naturally change the appearance of the query image, effectively satisfying the need for contrastive learning. Finally, we propose to incorporate a novel category-level contrastive loss that helps distinguish similar objects from different categories, in addition to classic instance-level contrastive loss. Our experiments demonstrate that our approach achieves the best performance on all the three popular IBSR benchmarks, including Pix3D, Stanford Cars, and Comp Cars, outperforming the previous state-of-the-art from 4% - 15% on retrieval accuracy.

Effective visual-semantic representation is critical to the image-text matching task. Various methods are proposed to develop image representation with more semantic concepts and a lot of progress has been achieved. However, the internal hierarchical structure in both image and text, which could effectively enhance the semantic representation, is rarely explored in the image-text matching task. In this work, we propose a Hierarchical Visual-Semantic Network (HVSN) with fine-grained semantic alignment to exploit the hierarchical structure. Specifically, we first model the spatial or semantic relationship between objects and aggregate them into visual semantic concepts by the Local Relational Attention (LRA) module. Then we employ Gated Recurrent Unit (GRU) to learn relationships between visual semantic concepts and generate the global image representation. For the text part, we develop phrase features from related words, then generate text representation by learning relationships between these phrases. Besides, the model is trained with joint optimization of image-text retrieval and phrase alignment task to capture the fine-grained interplay between vision and language. Our approach achieves state-of-the-art performance on Flickr30K and MS-COCO datasets. On Flickr30K, our approach outperforms the current state-of-the-art method by 3.9% relatively in text retrieval with image query and 1.3% relatively for image retrieval with text query (based on [email protected]). On MS-COCO, our HVSN improves image retrieval by 2.3% relatively and text retrieval by 1.2% relatively. Both quantitative and visual ablation studies are provided to verify the effectiveness of the proposed modules.

E-commerce business is revolutionizing our shopping experiences by providing convenient and straightforward services. One of the most fundamental problems is how to balance the demand and supply in market segments to build an efficient platform. While conventional machine learning models have achieved great success on data-sufficient segments, it may fail in a large-portion of segments in E-commerce platforms, where there are not sufficient records to learn well-trained models. In this paper, we tackle this problem in the context of market segment demand prediction. The goal is to facilitate the learning process in the target segments by leveraging the learned knowledge from data-sufficient source segments. Specifically, we propose a novel algorithm, RMLDP, to incorporate a multi-pattern fusion network (MPFN) with a meta-learning paradigm. The multi-pattern fusion network considers both local and seasonal temporal patterns for segment demand prediction. In the meta-learning paradigm, transferable knowledge is regarded as the model parameter initialization of MPFN, which are learned from diverse source segments. Furthermore, we capture the segment relations by combining data-driven segment representation and segment knowledge graph representation and tailor the segment-specific relations to customize transferable model parameter initialization. Thus, even with limited data, the target segment can quickly find the most relevant transferred knowledge and adapt to the optimal parameters. We conduct extensive experiments on two large-scale industrial datasets. The results justify that our RMLDP outperforms a set of state-of-the-art baselines. Besides, RMLDP has been deployed in Taobao, a real-world E-commerce platform. The online A/B testing results further demonstrate the practicality of RMLDP.

Interactive recommender systems that enable the interactions between users and the recommender system have attracted increasing research attention. Previous methods mainly focus on optimizing recommendation accuracy. However, they usually ignore the diversity of the recommendation results, thus usually results in unsatisfying user experiences. In this paper, we propose a novel diversified recommendation model, named Diversified Contextual Combinatorial Bandit (DC2B), for interactive recommendation with users' implicit feedback. Specifically, DC2B employs determinantal point process in the recommendation procedure to promote diversity of the recommendation results. To learn the model parameters, a Thompson sampling-type algorithm based on variational Bayesian inference is proposed. In addition, theoretical regret analysis is also provided to guarantee the performance of DC2B. Extensive experiments on real datasets are performed to demonstrate the effectiveness of the proposed method in balancing the recommendation accuracy and diversity.

Image-based 3D shape retrieval (IBSR) aims to find the corresponding 3D shape of a given 2D image from a large 3D shape database. The common routine is to map 2D images and 3D shapes into an embedding space and define (or learn) a shape similarity measure. While metric learning with some adaptation techniques seems to be a natural solution to shape similarity learning, the performance is often unsatisfactory for fine-grained shape retrieval. In the paper, we identify the source of the poor performance and propose a practical solution to this problem. We find that the shape difference between a negative pair is entangled with the texture gap, making metric learning ineffective in pushing away negative pairs. To tackle this issue, we develop a geometry-focused multi-view metric learning framework empowered by texture synthesis. The synthesis of textures for 3D shape models creates hard triplets, which suppress the adverse effects of rich texture in 2D images, thereby push the network to focus more on discovering geometric characteristics. Our approach shows state-of-the-art performance on a recently released large-scale 3D-FUTURE [1] repository, as well as three widely studied benchmarks, including Pix3D [2], Stanford Cars [3], and Comp Cars [4]. Codes will be made publicly available at: https://github.com/3D-FRONT-FUTURE/IBSR-texture.

With the rapid growth of e-commerce in recent years, e-commerce platforms are becoming a primary place for people to find, compare and ultimately purchase products. To improve online shopping experience for consumers and increase sales for sellers, it is important to understand user intent accurately and be notified of its change timely. In this way, the right information could be offered to the right person at the right time. To achieve this goal, we propose a unified deep intent prediction network, named EdgeDIPN, which is deployed at the edge, i.e., mobile device, and able to monitor multiple user intent with different granularity simultaneously in real-time. We propose to train EdgeDIPN with multi-task learning, by which EdgeDIPN can share representations between different tasks for better performance and saving edge resources in the meantime. In particular, we propose a novel task-specific attention mechanism which enables different tasks to pick out the most relevant features from different data sources. To extract the shared representations more effectively, we utilize two kinds of attention mechanisms, where the multi-level attention mechanism tries to identify the important actions within each data source and the inter-view attention mechanism learns the interactions between different data sources. In the experiments conducted on a large-scale industrial dataset, EdgeDIPN significantly outperforms the baseline solutions. Moreover, EdgeDIPN has been deployed in the operational system of Alibaba. Online A/B testing results in several business scenarios reveal the potential of monitoring user intent in real-time. To the best of our knowledge, EdgeDIPN is the first full-fledged real-time user intent understanding center deployed at the edge and serving hundreds of millions of users in a large-scale e-commerce platform.

This paper proposes a novel noisy label detection approach, named O2U-net, for deep neural networks without human annotations. Different from prior work which requires specifically designed noise-robust loss functions or networks, O2U-net is easy to implement but effective. It only requires adjusting the hyper-parameters of the deep network to make its status transfer from overfitting to underfitting (O2U) cyclically. The losses of each sample are recorded during iterations. The higher the normalized average loss of a sample, the higher the probability of being noisy labels. O2U-net is naturally compatible with active learning and other human annotation approaches. This introduces extra flexibility for learning with noisy labels. We conduct sufficient experiments on multiple datasets in various settings. The experimental results prove the state-of-the-art of O2S-net.

This paper proposes Personalized Diversity-promoting GAN (PD-GAN), a novel recommendation model to generate diverse, yet relevant recommendations. Specifically, for each user, a generator recommends a set of diverse and relevant items by sequentially sampling from a personalized Determinantal Point Process (DPP) kernel matrix. This kernel matrix is constructed by two learnable components: the general co-occurrence of diverse items and the user's personal preference to items. To learn the first component, we propose a novel pairwise learning paradigm using training pairs, and each training pair consists of a set of diverse items and a set of similar items randomly sampled from the observed data of all users. The second component is learnt through adversarial training against a discriminator which strives to distinguish between recommended items and the ground-truth sets randomly sampled from the observed data of the target user. Experimental results show that PD-GAN is superior to generate recommendations that are both diverse and relevant.

Increasing demand for fashion recommendation raises a lot of challenges for online shopping platforms and fashion communities. In particular, there exist two requirements for fashion outfit recommendation: the Compatibility of the generated fashion outfits, and the Personalization in the recommendation process. In this paper, we demonstrate these two requirements can be satisfied via building a bridge between outfit generation and recommendation. Through large data analysis, we observe that people have similar tastes in individual items and outfits. Therefore, we propose a Personalized Outfit Generation (POG) model, which connects user preferences regarding individual items and outfits with Transformer architecture. Extensive offline and online experiments provide strong quantitative evidence that our method outperforms alternative methods regarding both compatibility and personalization metrics. Furthermore, we deploy POG on a platform named Dida in Alibaba to generate personalized outfits for the users of the online application iFashion.

E-commerce platforms are becoming a primary place for people to find, compare and ultimately purchase products. One of the fundamental questions that arises in e-commerce is to predict user purchasing intent, which is an important part of user understanding and allows for providing better services for both sellers and customers. However, previous work cannot predict real-time user purchasing intent with a high accuracy, limited by the representation capability of traditional browse-interactive behavior adopted. In this paper, we propose a novel end-to-end deep network, named Deep Intent Prediction Network (DIPN), to predict real-time user purchasing intent. In particular, besides the traditional browse-interactive behavior, we collect a new type of user interactive behavior, called touch-interactive behavior, which can capture more fine-grained real-time user features. To combine these behavior effectively, we propose a hierarchical attention mechanism, where the bottom attention layer focuses on the inner parts of each behavior sequence while the top attention layer learns the inter-view relations between different behavior sequences. In addition, we propose to train DIPN with multi-task learning to better distinguish user behavior patterns. In the experiments conducted on a large-scale industrial dataset, DIPN significantly outperforms the baseline solutions. Notably, DIPN gains about 18.96% improvement on AUC than the state-of-the-art solution only using traditional browse-interactive behavior sequences. Moreover, DIPN has been deployed in the operational system of Taobao. Online A/B testing results with more than 12.9 millions of users reveal the potential of knowing users' real-time purchasing intent.

Recommender systems (RSs) have been the most important technology for increasing the business in Taobao, the largest online consumer-to-consumer (C2C) platform in China. There are three major challenges facing RS in Taobao: scalability, sparsity and cold start. In this paper, we present our technical solutions to address these three challenges. The methods are based on a well-known graph embedding framework. We first construct an item graph from users' behavior history, and learn the embeddings of all items in the graph. The item embeddings are employed to compute pairwise similarities between all items, which are then used in the recommendation process. To alleviate the sparsity and cold start problems, side information is incorporated into the graph embedding framework. We propose two aggregation methods to integrate the embeddings of items and the corresponding side information. Experimental results from offline experiments show that methods incorporating side information are superior to those that do not. Further, we describe the platform upon which the embedding methods are deployed and the workflow to process the billion-scale data in Taobao. Using A/B test, we show that the online Click-Through-Rates (CTRs) are improved comparing to the previous collaborative filtering based methods widely used in Taobao, further demonstrating the effectiveness and feasibility of our proposed methods in Taobao's live production environment.