With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus generate visual text that is style-consistent with the image. Previous methods often involve complex steps of specifying the text content and attributes, such as font size, color, and layout, without considering the stylistic consistency with the reference image. To address this, we propose UM-Text, a unified multimodal model for context understanding and visual text editing by natural language instructions. Specifically, we introduce a Visual Language Model (VLM) to process the instruction and reference image, so that the text content and layout can be elaborately designed according to the context information. To generate an accurate and harmonious visual text image, we further propose the UM Encoder to combine the embeddings of various condition information, where the combination is automatically configured by VLM according to the input instruction. During training, we propose a regional consistency loss to offer more effective supervision for glyph generation on both latent and RGB space, and design a tailored three-stage training strategy to further enhance model performance. In addition, we contribute the UM-DATA-200K, a large-scale visual text image dataset on diverse scenes for model training. Extensive qualitative and quantitative results on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance.

Vision Transformer (ViT) on object re-identification (ReID) has attracted significant attention recently. However, ViT-based ReID substantially increases computational complexity, imposing significant burdens during training and inference. This paper presents an efficient and effective ViT-based backbone for ReID tasks, called the Locally Enhanced Vision Transformer (LEViT). ViT models typically emphasize global relationship modeling, yet ReID tasks are more sensitive to local information. To address this gap, we propose a Locally Enhanced (LE) block to enhance local information by performing self-attention within local split windows. Since part-based models dominate ReID, calculating self-attention across all patches is computationally inefficient. We also replace the traditional Query-Key-Value projector with the Group Convolution (G-Conv) projector, enabling the model to capture local details more efficiently. Furthermore, G-Conv is integrated into the channel MLP to strengthen local feature sensitivity. Using these components, we develop two LEViT variants: LEViT-S and LEViT-L. To our knowledge, LEViT is the first highly adaptable ViT backbone for ReID tasks. Experimental evaluations demonstrate the effectiveness in five ReID datasets: Market1501, DukeMTMC, MSMT17, VeRi-776, and VehicleID. Notably, LEViT-S outperforms TransReID while requiring less than 10% computational complexity. Furthermore, LEViT obtains the state-of-the-art on three deep metric learning datasets: CUB-200-2011, Cars196, and University-1652. Our code will be available athttps://github.com/YuhuiWang99/LEViT.

Recently, the accuracy of image-text matching has been greatly improved by multimodal pretrained models, all of which use millions or billions of paired images and texts for supervised model learning. Different from them, human brains can well match images with texts using their stored multimodal knowledge. Inspired by that, this paper studies a new scenario as unpaired image-text matching, in which paired images and texts are assumed to be unavailable during model learning. To deal with it, we accordingly propose a simple yet effective method namely Multimodal Aligned Conceptual Knowledge (MACK). First, we collect a set of words and their related image regions from publicly available datasets, and compute prototypical region representations to obtain pretrained general knowledge. To make the obtained knowledge better suit for certain datasets, we refine it using unpaired images and texts in a self-supervised learning manner to obtain fine-tuned domain knowledge. Then, to match given images with texts based on the knowledge, we represent parsed words in the texts by prototypical region representations, and compute region-word similarity scores. At last, the scores are aggregated based on bidirectional similarity pooling into an image-text similarity score, which can be directly used for unpaired image-text matching. The proposed MACK is complementary with existing models, which can be easily extended as a re-ranking method to substantially improve their performance of zero-shot and cross-dataset image-text matching.

Consistent editing of real images is a challenging task, as it requires performing non-rigid edits (e.g., changing postures) to the main objects in the input image without changing their identity or attributes. To guarantee consistent attributes, some existing methods fine-tune the entire model or the textual embedding for structural consistency, but they are time-consuming and fail to perform non-rigid edits. Other works are tuning-free, but their performances are weakened by the quality of Denoising Diffusion Implicit Model (DDIM) reconstruction, which often fails in real-world scenarios. In this paper, we present a novel approach called Tuning-free Inversion-enhanced Control (TIC), which directly correlates features from the inversion process with those from the sampling process to mitigate the inconsistency in DDIM reconstruction. Specifically, our method effectively obtains inversion features from the key and value features in the self-attention layers, and enhances the sampling process by these inversion features, thus achieving accurate reconstruction and content-consistent editing. To extend the applicability of our method to general editing scenarios, we also propose a mask-guided attention concatenation strategy that combines contents from both the inversion and the naive DDIM editing processes. Experiments show that the proposed method outperforms previous works in reconstruction and consistent editing, and produces impressive results in various settings.

In this paper, we address a complex but practical scenario in Active Learning (AL) known as open-set AL, where the unlabeled data consists of both in-distribution (ID) and out-of-distribution (OOD) samples. Standard AL methods will fail in this scenario as OOD samples are highly likely to be regarded as uncertain samples, leading to their selection and wasting of the budget. Existing methods focus on selecting the highly likely ID samples, which tend to be easy and less informative. To this end, we introduce two criteria, namely contrastive confidence and historical divergence, which measure the possibility of being ID and the hardness of a sample, respectively. By balancing the two proposed criteria, highly informative ID samples can be selected as much as possible. Furthermore, unlike previous methods that require additional neural networks to detect the OOD samples, we propose a contrastive clustering framework that endows the classifier with the ability to identify the OOD samples and further enhances the network's representation learning. The experimental results demonstrate that the proposed method achieves state-of-the-art performance on several benchmark datasets.

It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it. However, current image captioning methods usually consider the generation of all words in a sentence sequentially and equally. In this paper, we propose an uncertainty-aware image captioning framework, which parallelly and iteratively operates insertion of discontinuous candidate words between existing words from easy to difficult until converged. We hypothesize that high-uncertainty words in a sentence need more prior information to make a correct decision and should be produced at a later stage. The resulting non-autoregressive hierarchy makes the caption generation explainable and intuitive. Specifically, we utilize an image-conditioned bag-of-word model to measure the word uncertainty and apply a dynamic programming algorithm to construct the training pairs. During inference, we devise an uncertainty-adaptive parallel beam search technique that yields an empirically logarithmic time complexity. Extensive experiments on the MS COCO benchmark reveal that our approach outperforms the strong baseline and related methods on both captioning quality as well as decoding speed.

Masked Auto-Encoder (MAE) pretraining methods randomly mask image patches and then train a vision Transformer to reconstruct the original pixels based on the unmasked patches. While they demonstrates impressive performance for downstream vision tasks, it generally requires a large amount of training resource. In this paper, we introduce a novel Generative Adversarial Networks alike framework, referred to as GAN-MAE, where a generator is used to generate the masked patches according to the remaining visible patches, and a discriminator is employed to predict whether the patch is synthesized by the generator. We believe this capacity of distinguishing whether the image patch is predicted or original is benefit to representation learning. Another key point lies in that the parameters of the vision Transformer backbone in the generator and discriminator are shared. Extensive experiments demonstrate that adversarial training of GAN-MAE framework is more efficient and accordingly outperforms the standard MAE given the same model size, training data, and computation resource. The gains are substantially robust for different model sizes and datasets, in particular, a ViT-B model trained with GAN-MAE for 200 epochs outperforms the MAE with 1600 epochs on fine-tuning top-1 accuracy of ImageNet-1k with much less FLOPs. Besides, our approach also works well at transferring downstream tasks.

Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target samples. Conventional AL methods do not consider the existence of domain shift, and hence, fail to identify the truly valuable samples in the context of domain adaptation. To accommodate active learning and domain adaption, the two naturally different tasks, in a collaborative framework, we advocate that a customized learning strategy for the target data is the key to the success of ADA solutions. We present Divide-and-Adapt (DiaNA), a new ADA framework that partitions the target instances into four categories with stratified transferable properties. With a novel data subdivision protocol based on uncertainty and domainness, DiaNA can accurately recognize the most gainful samples. While sending the informative instances for annotation, DiaNA employs tailored learning strategies for the remaining categories. Furthermore, we propose an informativeness score that unifies the data partitioning criteria. This enables the use of a Gaussian mixture model (GMM) to automatically sample unlabeled data into the proposed four categories. Thanks to the “divide-and-adapt” spirit, DiaNA can handle data with large variations of domain gap. In addition, we show that DiaNA can generalize to different domain adaptation settings, such as unsupervised domain adaptation (UDA), semi-supervised domain adaptation (SSDA), source-free domain adaptation (SFDA), etc.

RGB-T tracking aims to leverage the mutual enhancement and complement ability of RGB and TIR modalities for improving the tracking process in various scenarios, where cross-modal interaction is the key component. Some previous methods concatenate the RGB and TIR search region features directly to perform a coarse interaction process with redundant background noises introduced. Many other methods sample candidate boxes from search frames and conduct various fusion approaches on isolated pairs of RGB and TIR boxes, which limits the cross-modal interaction within local regions and brings about inadequate context modeling. To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module which exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts. Original templates are also updated with enriched multimodal contexts from the template medium. Our TBSI module is inserted into a ViT backbone for joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate our method achieves new state-of-the-art performances. Code is available at https://github.com/RyanHTR/TBSI.

While recent neural image captioning models have shown great promise in terms of automatic metrics, they still struggle with generating generic sentences, which limits their use to only a handful of simple scenarios. On the other hand, negative training has been suggested as an effective way to prevent models from producing frequent yet meaningless sentences. However, when applied to image captioning, this approach may overlook low-frequency but generic and vague sentences, which can be problematic when dealing with diverse and changeable visual scenes. In this paper, we introduce a approach to improve image captioning by integrating negative knowledge that focuses on preventing the model from producing undesirable generic descriptions while addressing previous limitations. We accomplish this by training a negative teacher model that generates image-wise generic sentences with retrieval entropy-filtered data. Subsequently, the student model is required to maximize the distance with multi-level negative knowledge transferring for optimal guiding. Empirical results evaluated on MS COCO benchmark confirm that our plug-and-play framework incorporating unlikely negative knowledge leads to significant improvements in both accuracy and diversity, surpassing previous state-of-the-art methods for distinctive image captioning.

Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect of PNG is the visual-linguistic interaction between image and caption. The previous two-stage method aggregates visual contexts from offline-generated mask proposals to phrase features, which tend to be noisy and fragmentary. The recent one-stage method aggregates only pixel contexts from image features to phrase features, which may incur semantic misalignment due to lacking object priors. To realize more comprehensive visual-linguistic interaction, we propose to enrich phrases with coupled pixel and object contexts by designing a Phrase-Pixel-Object Transformer Decoder (PPO-TD), where both fine-grained part details and coarse-grained entity clues are aggregated to phrase features. In addition, we also propose a Phrase-Object Contrastive Loss (POCL) to pull closer the matched phrase-object pairs and push away unmatched ones for aggregating more precise object contexts from more phrase-relevant object tokens. Extensive experiments on the PNG benchmark show our method achieves new state-of-the-art performance with large margins.

Recent works on personalized text-to-image generation usually learn to bind a special token with specific subjects or styles of a few given images by tuning its embedding through gradient descent. It is natural to question whether we can optimize the textual inversions by only accessing the process of model inference. As only requiring the forward computation to determine the textual inversion retains the benefits of less GPU memory, simple deployment, and secure access for scalable models. In this paper, we introduce a gradient-free framework to optimize the continuous textual inversion in an iterative evolutionary strategy. Specifically, we first initialize an appropriate token embedding for textual inversion with the consideration of visual and text vocabulary information. Then, we decompose the optimization of evolutionary strategy into dimension reduction of searching space and non-convex gradient-free optimization in subspace, which significantly accelerates the optimization process with negligible performance loss. Experiments in several creative applications demonstrate that the performance of text-to-image model equipped with our proposed gradient-free method is comparable to that of gradient-based counterparts with variant GPU/CPU platforms, flexible employment, as well as computational efficiency.

Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos. Previous methods either depend on 3D ConvNets or incorporate additional 2D ConvNets as encoders to extract mixed spatial-temporal features. However, these methods suffer from spatial misalignment or false distractors due to delayed and implicit spatial-temporal interaction occurring in the decoding phase. To tackle these limitations, we propose a Language-Bridged Duplex Transfer (LBDT) module which utilizes language as an intermediary bridge to accomplish explicit and adaptive spatial-temporal interaction earlier in the encoding phase. Concretely, cross-modal attention is performed among the temporal encoder, referring words and the spatial encoder to aggregate and transfer language-relevant motion and appearance information. In addition, we also propose a Bilateral Channel Activation (BCA) module in the decoding phase for further denoising and highlighting the spatial-temporal consistent features via channel-wise activation. Extensive experiments show our method achieves new state-of-the-art performances on four popular benchmarks with 6.8% and 6.9% absolute AP gains on A2D Sentences and J-HMDB Sentences respectively, while consuming around 7× less computational overhead11https://github.com/dzh19990407/LBDT.

Panoptic Narrative Grounding (PNG) is an emerging task whose goal is to segment visual objects of things and stuff categories described by dense narrative captions of a still image. The previous two-stage approach first extracts segmentation region proposals by an off-the-shelf panoptic segmentation model, then conducts coarse region-phrase matching to ground the candidate regions for each noun phrase. However, the two-stage pipeline usually suffers from the performance limitation of low-quality proposals in the first stage and the loss of spatial details caused by region feature pooling, as well as complicated strategies designed for things and stuff categories separately. To alleviate these drawbacks, we propose a one-stage end-to-end Pixel-Phrase Matching Network (PPMN), which directly matches each phrase to its corresponding pixels instead of region proposals and outputs panoptic segmentation by simple combination. Thus, our model can exploit sufficient and finer cross-modal semantic correspondence from the supervision of densely annotated pixel-phrase pairs rather than sparse region-phrase pairs. In addition, we also propose a Language-Compatible Pixel Aggregation (LCPA) module to further enhance the discriminative ability of phrase features through multi-round refinement, which selects the most compatible pixels for each phrase to adaptively aggregate the corresponding visual context. Extensive experiments show that our method achieves new state-of-the-art performance on the PNG benchmark with 4.0 absolute Average Recall gains.

BiSeNet [28], [27] has been proved to be a popular two-stream network for real-time segmentation. However, its principle of adding an extra path to encode spatial information is time-consuming, and the backbones borrowed from pretrained tasks, e.g., image classification, may be inefficient for image segmentation due to the deficiency of task-specific design. To handle these problems, we propose a novel and efficient structure named Short-Term Dense Concatenate network (STDC network) by removing structure redundancy. Specifically, we gradually reduce the dimension of feature maps and use the aggregation of them for image representation, which forms the basic module of STDC network. In the decoder, we propose a Detail Aggregation module by integrating the learning of spatial information into low-level layers in single-stream manner. Finally, the low-level features and deep features are fused to predict the final segmentation results. Extensive experiments on Cityscapes and CamVid dataset demonstrate the effectiveness of our method by achieving promising trade-off between segmentation accuracy and inference speed. On Cityscapes, we achieve 71.9% mIoU on the test set with a speed of 250.4 FPS on NVIDIA GTX 1080Ti, which is 45.2% faster than the latest methods, and achieve 76.8% mIoU with 97.0 FPS while inferring on higher resolution images. Code is available at https://github.com/MichaelFan01/STDC-Seg.

Weakly Supervised Semantic Segmentation (WSSS) with image-level annotation uses class activation maps from the classifier as pseudo-labels for semantic segmentation. However, such activation maps usually highlight the local discriminative regions rather than the whole object, which deviates from the requirement of semantic segmentation. To explore more comprehensive class-specific activation maps, we propose an Embedded Discriminative Attention Mechanism (EDAM) by integrating the activation map generation into the classification network directly for WSSS. Specifically, a Discriminative Activation (DA) layer is designed to explicitly produce a series of normalized class-specific masks, which are then used to generate class-specific pixel-level pseudo-labels demanded in segmentation. For learning the pseudo-labels, the masks are multiplied with the feature maps after the backbone to generate the discriminative activation maps, each of which encodes the specific information of the corresponding category in the input images. Given such class-specific activation maps, a Collaborative Multi-Attention (CMA) module is proposed to extract the collaborative information of each given category from images in a batch. In inference, we directly use the activation masks from the DA layer as pseudo-labels for segmentation. Based on the generated pseudo-labels, we achieve the mIoU of 70.60% on PASCAL VOC 2012 segmentation testset, which is the new state-of-the-art, to our best knowledge. Code and pre-trained models are available online soon.

Face alignment acts as an important task in computer vision. Regression-based methods currently dominate the approach to solving this problem, which generally employ a series of mapping functions from the face appearance to iteratively update the face shape hypothesis. One keypoint here is thus how to perform the regression procedure. In this work, we formulate this regression procedure as a sparse coding problem. We learn two relational dictionaries, one for the face appearance and the other one for the face shape, with coupled reconstruction coefficient to capture their underlying relationships. To deploy this model for face alignment, we derive the relational dictionaries in a stage-wised manner to perform close-loop refinement of themselves, i.e., the face appearance dictionary is first learned from the face shape dictionary and then used to update the face shape hypothesis, and the updated face shape dictionary from the shape hypothesis is in return used to refine the face appearance dictionary. To improve the model accuracy, we extend this model hierarchically from the whole face shape to face part shapes, thus both the global and local view variations of a face are captured. To locate facial landmarks under occlusions, we further introduce an occlusion dictionary into the face appearance dictionary to recover face shape from partially occluded face appearance. The occlusion dictionary is learned in a data driven manner from background images to represent a set of elemental occlusion patterns, a sparse combination of which models various practical partial face occlusions. By integrating all these technical innovations, we obtain a robust and accurate approach to locate facial landmarks under different face views and possibly severe occlusions for face images in the wild. Extensive experimental analyses and evaluations on different benchmark datasets, as well as two new datasets built by ourselves, have demonstrated the robustness and accuracy of our proposed model, especially for face images with large view variations and/or severe occlusions.

In this paper, we present a novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more complicated in network structure yet with less inference complexity. The core idea is to equip each original convolutional layer with another low-cost collaborative layer (LCCL), and the element-wise multiplication of the ReLU outputs of these two parallel layers produces the layer-wise output. The combined layer is potentially more discriminative than the original convolutional layer, and its inference is faster for two reasons: 1) the zero cells of the LCCL feature maps will remain zero after element-wise multiplication, and thus it is safe to skip the calculation of the corresponding high-cost convolution in the original convolutional layer; 2) LCCL is very fast if it is implemented as a 1 × 1 convolution or only a single filter shared by all channels. Extensive experiments on the CIFAR-10, CIFAR-100 and ILSCRC-2012 benchmarks show that our proposed network structure can accelerate the inference process by 32% on average with negligible performance drop.

Convolutional Neural Network (CNN) has demonstrated promising performance in single-label image classification tasks. However, how CNN best copes with multi-label images still remains an open problem, mainly due to the complex underlying object layouts and insufficient multi-label training images. In this work, we propose a flexible deep CNN infrastructure, called Hypotheses-CNN-Pooling (HCP), where an arbitrary number of object segment hypotheses are taken as the inputs, then a shared CNN is connected with each hypothesis, and finally the CNN output results from different hypotheses are aggregated with max pooling to produce the ultimate multi-label predictions. Some unique characteristics of this flexible deep CNN infrastructure include: 1) no ground-truth bounding box information is required for training; 2) the whole HCP infrastructure is robust to possibly noisy and/or redundant hypotheses; 3) the shared CNN is flexible and can be well pre-trained with a large-scale single-label image dataset, e.g., ImageNet; and 4) it may naturally output multi-label prediction results. Experimental results on Pascal VOC 2007 and VOC 2012 multi-label image datasets well demonstrate the superiority of the proposed HCP infrastructure over other state-of-the-arts. In particular, the mAP reaches 90.5% by HCP only and 93.2% after the fusion with our complementary result in [44] based on hand-crafted features on the VOC 2012 dataset.

This paper aims at developing an integrated system for clothing co-parsing (CCP), in order to jointly parse a set of clothing images (unsegmented but annotated with tags) into semantic configurations. A novel data-driven system consisting of two phases of inference is proposed. The first phase, referred as “image cosegmentation,” iterates to extract consistent regions on images and jointly refines the regions over all images by employing the exemplar-SVM technique [1]. In the second phase (i.e., “region colabeling”), we construct a multiimage graphical model by taking the segmented regions as vertices, and incorporating several contexts of clothing configuration (e.g., item locations and mutual interactions). The joint label assignment can be solved using the efficient Graph Cuts algorithm. In addition to evaluate our framework on the Fashionista dataset [2], we construct a dataset called the SYSU-Clothes dataset consisting of 2098 high-resolution street fashion photos to demonstrate the performance of our system. We achieve 90.29%/88.23% segmentation accuracy and 65.52%/63.89% recognition rate on the Fashionista and the SYSU-Clothes datasets, respectively, which are superior compared with the previous methods. Furthermore, we apply our method on a challenging task, i.e., cross-domain clothing retrieval: given user photo depicting a clothing image, retrieving the same clothing items from online shopping stores based on the fine-grained parsing results.

We address the problem of describing people based on fine-grained clothing attributes. This is an important problem for many practical applications, such as identifying target suspects or finding missing people based on detailed clothing descriptions in surveillance videos or consumer photos. We approach this problem by first mining clothing images with fine-grained attribute labels from online shopping stores. A large-scale dataset is built with about one million images and fine-detailed attribute sub-categories, such as various shades of color (e.g., watermelon red, rosy red, purplish red), clothing types (e.g., down jacket, denim jacket), and patterns (e.g., thin horizontal stripes, houndstooth). As these images are taken in ideal pose/lighting/background conditions, it is unreliable to directly use them as training data for attribute prediction in the domain of unconstrained images captured, for example, by mobile phones or surveillance cameras. In order to bridge this gap, we propose a novel double-path deep domain adaptation network to model the data from the two domains jointly. Several alignment cost layers placed inbetween the two columns ensure the consistency of the two domain features and the feasibility to predict unseen attribute categories in one of the domains. Finally, to achieve a working system with automatic human body alignment, we trained an enhanced RCNN-based detector to localize human bodies in images. Our extensive experimental evaluation demonstrates the effectiveness of the proposed approach for describing people based on fine-grained clothing attributes.

We address the problem of cross-domain image retrieval, considering the following practical application: given a user photo depicting a clothing image, our goal is to retrieve the same or attribute-similar clothing items from online shopping stores. This is a challenging problem due to the large discrepancy between online shopping images, usually taken in ideal lighting/pose/background conditions, and user photos captured in uncontrolled conditions. To address this problem, we propose a Dual Attribute-aware Ranking Network (DARN) for retrieval feature learning. More specifically, DARN consists of two sub-networks, one for each domain, whose retrieval feature representations are driven by semantic attribute learning. We show that this attribute-guided learning is a key factor for retrieval accuracy improvement. In addition, to further align with the nature of the retrieval problem, we impose a triplet visual similarity constraint for learning to rank across the two subnetworks. Another contribution of our work is a large-scale dataset which makes the network learning feasible. We exploit customer review websites to crawl a large set of online shopping images and corresponding offline user photos with fine-grained clothing attributes, i.e., around 450,000 online shopping images and about 90,000 exact offline counterpart images of those online ones. All these images are collected from real-world consumer websites reflecting the diversity of the data modality, which makes this dataset unique and rare in the academic community. We extensively evaluate the retrieval performance of networks in different configurations. The top-20 retrieval accuracy is doubled when using the proposed DARN other than the current popular solution using pre-trained CNN features only (0.570 vs. 0.268).

We present a robust model to locate facial landmarks under different views and possibly severe occlusions. To build reliable relationships between face appearance and shape with large view variations, we propose to formulate face alignment as an l1-induced Stagewise Relational Dictionary (SRD) learning problem. During each training stage, the SRD model learns a relational dictionary to capture consistent relationships between face appearance and shape, which are respectively modeled by the pose-indexed image features and the shape displacements for current estimated landmarks. During testing, the SRD model automatically selects a sparse set of the most related shape displacements for the testing face and uses them to refine its shape iteratively. To locate facial landmarks under occlusions, we further propose to learn an occlusion dictionary to model different kinds of partial face occlusions. By deploying the occlusion dictionary into the SRD model, the alignment performance for occluded faces can be further improved. Our algorithm is simple, effective, and easy to implement. Extensive experiments on two benchmark datasets and two newly built datasets have demonstrated its superior performances over the state-of-the-art methods, especially for faces with large view variations and/or occlusions.

In this demo, we present Deep Search, an attribute-aware fashion-related retrieval system, based on the convolutional neural network by taking clothes as a concrete example. In this system, the visual appearance and semantic attributes of products can be seamlessly integrated into our model in a "dividing and combining" manner. Rather than modelling one attribute per classifier, we design a holistic tree-structure network for exploiting multiple attributes simultaneously, with each branch of network corresponding to one attribute. Therefore, the high-level feature from the conjunction layer of the network can comprehensively preserve both the visual and semantic information of products. The promising retrieval results indicate the great potential of neural feature for attribute-aware retrieval task. The supplementary slides can be found in http://goo.gl/zpobN6.

In this paper we address the problem of automatically parsing the fashion images with weak supervision from the user-generated color-category tags such as “red jeans” and “white T-shirt”. This problem is very challenging due to the large diversity of fashion items and the absence of pixel-level tags, which make the traditional fully supervised algorithms inapplicable. To solve the problem, we propose to combine the human pose estimation module, the MRF-based color and category inference module and the (super)pixel-level category classifier learning module to generate multiple well-performing category classifiers, which can be directly applied to parse the fashion items in the images. Besides, all the training images are parsed with color-category labels and the human poses of the images are estimated during the model learning phase in this work. We also construct a new fashion image dataset called Colorful-Fashion, in which all 2,682 images are labeled with pixel-level color-category labels. Extensive experiments on this dataset clearly show the effectiveness of the proposed method for the weakly supervised fashion parsing task.

Taking the shoe as a concrete example, we present an innovative product retrieval system that leverages object detection and retrieval techniques to support a brand-new online shopping experience in this article. The system, called Circle & Search, enables users to naturally indicate any preferred product by simply circling the product in images as the visual query, and then returns visually and semantically similar products to the users. The system is characterized by introducing attributes in both the detection and retrieval of the shoe. Specifically, we first develop an attribute-aware part-based shoe detection model. By maintaining the consistency between shoe parts and attributes, this shoe detector has the ability to model high-order relations between parts and thus the detection performance can be enhanced. Meanwhile, the attributes of this detected shoe can also be predicted as the semantic relations between parts. Based on the result of shoe detection, the system ranks all the shoes in the repository using an attribute refinement retrieval model that takes advantage of query-specific information and attribute correlation to provide an accurate and robust shoe retrieval. To evaluate this retrieval system, we build a large dataset with 17,151 shoe images, in which each shoe is annotated with 10 shoe attributes e.g., heel height, heel shape, sole shape, etc.). According to the experimental result and the user study, our Circle & Search system achieves promising shoe retrieval performance and thus significantly improves the users' online shopping experience.

Nowadays, content-based retrieval methods are still the development trend of the traditional retrieval systems. Image labels, as one of the most popular approaches for the semantic representation of images, can fully capture the representative information of images. To achieve the high performance of retrieval systems, the precise annotation for images becomes inevitable. However, as the massive number of images in the Internet, one cannot annotate all the images without a scalable and flexible (i.e., training-free) annotation method. In this paper, we particularly investigate the problem of accelerating sparse coding based scalable image annotation, whose off-the-shelf solvers are generally inefficient on large-scale dataset. By leveraging the prior that most reconstruction coefficients should be zero, we develop a general and efficient framework to derive an accurate solution to the large-scale sparse coding problem through solving a series of much smaller-scale subproblems. In this framework, an active variable set, which expands and shrinks iteratively, is maintained, with each snapshot of the active variable set corresponding to a subproblem. Meanwhile, the convergence of our proposed framework to global optimum is theoretically provable. To further accelerate the proposed framework, a sub-linear time complexity hashing strategy, e.g. Locality-Sensitive Hashing, is seamlessly integrated into our framework. Extensive empirical experiments on NUS-WIDE and IMAGENET datasets demonstrate that the orders-of-magnitude acceleration is achieved by the proposed framework for large-scale image annotation, along with zero/negligible accuracy loss for the cases without/with hashing speed-up, compared to the expensive off-the-shelf solvers.

Understanding search intents of users through their condensed short queries has attracted much attention both in academia and industry. The search intents of users are generally assumed to be associated with various query patterns, such as "MobileName price", where "MobileName" could be any named entity of mobile phone model and this pattern indicates that the user intends to buy a mobile phone. However, discovering the query intent patterns for general search is challenging mainly due to the difficulty in collecting sufficient training data for learning query patterns across a large number of searchable domains. In this work, we propose Cross Domain Random Walk (CDRW) algorithm, which is semi-supervised, to discover the query intent patterns across different domains from search engine click-through log data. Starting with some manually tagged seed queries in one or more independent domains, CDRW takes the query patterns as bridge and propagates the transition probability across domains to collect the query intent patterns among different domains based on the assumption that "users who have similar intent in different but similar domains will have high probability to share similar query patterns across domains". Different from classical random walk algorithms, CDRW walks across different domains to disseminate the shared knowledge in a transfer learning manner. Extensive experiment results on real log data of a commercial search engine well validate the effectiveness and efficiency of the proposed algorithm.