Multi-view based shape descriptors have achieved impressive performance for 3D shape retrieval. The core of view-based methods is to interpret 3D structures through 2D observations. However, most existing methods pay more attention to discriminative models and none of them necessarily incorporate the 3D properties of the objects. To resolve this problem, we propose an encoder-decoder recurrent feature aggregation network (ERFA-Net) to emphasize the 3D properties of 3D shapes in multi-view features aggregation. In our network, a view sequence of the shape is trained to encode a discriminative shape embedding and estimate unseen rendered views of any viewpoints. This generation task gives an effective supervision which makes the network exploit 3D properties of shapes through various 2D images. During feature aggregation, a discriminative feature representation across multiple views is effectively exploited based on LSTM network. The proposed 3D representation has following advantages against other state-of-the-art: 1) it performs robust discrimination under the existence of noise such as view missing and occlusion, because of the improvement brought by 3D properties. 2) it has strong generative capabilities, which is useful for various 3D shape tasks. We evaluate ERFA-Net on two popular 3D shape datasets, ModelNet and ShapeNetCore55, and ERFA-Net outperforms the state-of-the-art methods significantly. Extensive experiments show the effectiveness and robustness of the proposed 3D representation.

A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power of the deeply learned features and weakens the undesired modality discrepancy by jointly optimizing a ranking loss and a softmax loss for both homogeneous and heterogeneous modalities. The ranking loss consists of intra-modality and cross-modality triplet losses, and it reduces both the intra-modality and cross-modality feature variations. Furthermore, the correlations between RGB and depth data are embedded in the c-ConvNet, and can be retrieved by either of the modalities and contribute to the recognition in the case even only one of the modalities is available. The proposed method was extensively evaluated on two large RGB-D action recognition datasets, ChaLearn LAP IsoGD and NTU RGB+D datasets, and one small dataset, SYSU 3D HOI, and achieved state-of-the-art results.

Recently, hashing methods have been widely used in large-scale image retrieval. However, most existing supervised hashing methods do not consider the hierarchical relation of labels,which means that they ignored the rich semantic information stored in the hierarchy. Moreover, most of previous works treat each bit in a hash code equally, which does not meet the scenario of hierarchical labeled data. To tackle the aforementioned problems, in this paper, we propose a novel deep hashing method, called supervised hierarchical deep hashing (SHDH), to perform hash code learning for hierarchical labeled data. Specifically, we define a novel similarity formula for hierarchical labeled data by weighting each level, and design a deep neural network to obtain a hash code for each data point. Extensive experiments on two real-world public datasets show that the proposed method outperforms the state-of-the-art baselines in the image retrieval task.

A single image captures the appearance and position of multiple entities in a scene as well as their complex interactions. As a consequence, natural language grounded in visual contexts tends to be diverse---with utterances differing as focus shifts to specific objects, interactions, or levels of detail. Recently, neural sequence models such as RNNs and LSTMs have been employed to produce visually-grounded language. Beam Search, the standard work-horse for decoding sequences from these models, is an approximate inference algorithm that decodes the top-B sequences in a greedy left-to-right fashion. In practice, the resulting sequences are often minor rewordings of a common utterance, failing to capture the multimodal nature of source images. To address this shortcoming, we propose Diverse Beam Search (DBS), a diversity promoting alternative to BS for approximate inference. DBS produces sequences that are significantly different from each other by incorporating diversity constraints within groups of candidate sequences during decoding; moreover, it achieves this with minimal computational or memory overhead. We demonstrate that our method improves both diversity and quality of decoded sequences over existing techniques on two visually-grounded language generation tasks---image captioning and visual question generation---particularly on complex scenes containing diverse visual content. We also show similar improvements at language-only machine translation tasks, highlighting the generality of our approach.

We study domain-specific video streaming. Specifically, we target a streaming setting where the videos to be streamed from a server to a client are all in the same domain and they have to be compressed to a small size for low-latency transmission. Several popular video streaming services, such as the video game streaming services of GeForce Now and Twitch, fall in this category. While conventional video compression standards such as H.264 are commonly used for this task, we hypothesize that one can leverage the property that the videos are all in the same domain to achieve better video quality. Based on this hypothesis, we propose a novel video compression pipeline. Specifically, we first apply H.264 to compress domain-specific videos. We then train a novel binary autoencoder to encode the leftover domain-specific residual information frame-by-frame into binary representations. These binary representations are then compressed and sent to the client together with the H.264 stream. In our experiments, we show that our pipeline yields consistent gains over standard H.264 compression across several benchmark datasets while using the same channel bandwidth.

The gap between sensing patterns of different face modalities remains a challenging problem in heterogeneous face recognition (HFR). This paper proposes an adversarial discriminative feature learning framework to close the sensing gap via adversarial learning on both raw-pixel space and compact feature space. This framework integrates cross-spectral face hallucination and discriminative feature learning into an end-to-end adversarial network. In the pixel space, we make use of generative adversarial networks to perform cross-spectral face hallucination. An elaborate two-path model is introduced to alleviate the lack of paired images, which gives consideration to both global structures and local textures. In the feature space, an adversarial loss and a high-order variance discrepancy loss are employed to measure the global and local discrepancy between two heterogeneous distributions respectively. These two losses enhance domain-invariant feature learning and modality independent noise removing. Experimental results on three NIR-VIS databases show that our proposed approach outperforms state-of-the-art HFR methods, without requiring of complex network or large-scale training dataset.

One of the major restrictions on the performance of video-based person re-id is partial noise caused by occlusion, blur and illumination. Since different spatial regions of a single frame have various quality, and the quality of the same region also varies across frames in a tracklet, a good way to address the problem is to effectively aggregate complementary information from all frames in a sequence, using better regions from other frames to compensate the influence of an image region with poor quality. To achieve this, we propose a novel Region-based Quality Estimation Network (RQEN), in which an ingenious training mechanism enables the effective learning to extract the complementary region-based information between different frames. Compared with other feature extraction methods, we achieved comparable results of 92.4%, 76.1% and 77.83% on the PRID 2011, iLIDS-VID and MARS, respectively. In addition, to alleviate the lack of clean large-scale person re-id datasets for the community, this paper also contributes a new high-quality dataset, named "Labeled Pedestrian in the Wild (LPW)" which contains 7,694 tracklets with over 590,000 images. Despite its relatively large scale, the annotations also possess high cleanliness. Moreover, it's more challenging in the following aspects: the age of characters varies from childhood to elderhood; the postures of people are diverse, including running and cycling in addition to the normal walking state.

With an abundance of research papers in deep learning, reproducibility or adoption of the existing works becomes a challenge. This is due to the lack of open source implementations provided by the authors. Even if the source code is available, then re-implementing research papers in a different library is a daunting task. To address these challenges, we propose a novel extensible approach, DLPaper2Code, to extract and understand deep learning design flow diagrams and tables available in a research paper and convert them to an abstract computational graph. The extracted computational graph is then converted into execution ready source code in both Keras and Caffe, in real-time. An arXiv-like website is created where the automatically generated designs is made publicly available for 5,000 research papers. The generated designs could be rated and edited using an intuitive drag-and-drop UI framework in a crowd sourced manner. To evaluate our approach, we create a simulated dataset with over 216,000 valid deep learning design flow diagrams using a manually defined grammar. Experiments on the simulated dataset show that the proposed framework provide more than 93% accuracy in flow diagram content extraction.

The ability of machine-based agents to play games in human-like fashion is considered a benchmark of progress in AI. In this paper, we introduce the first computational model aimed at Pictionary, the popular word-guessing social game. We first introduce Sketch-QA, an elementary version of Visual Question Answering task. Styled after Pictionary, Sketch-QA uses incrementally accumulated sketch stroke sequences as visual data. Notably, Sketch-QA involves asking a fixed question ("What object is being drawn?") and gathering open-ended guess-words from human guessers. To mimic Pictionary-style guessing, we propose a deep neural model which generates guess-words in response to temporally evolving human-drawn sketches. Our model even makes human-like mistakes while guessing, thus amplifying the human mimicry factor. We evaluate our model on the large-scale guess-word dataset generated via Sketch-QA task and compare with various baselines. We also conduct a Visual Turing Test to obtain human impressions of the guess-words generated by humans and our model. Experimental results demonstrate the promise of our approach for Pictionary and similarly themed games.

Counting people in dense crowds is a demanding task even for humans. This is primarily due to the large variability in appearance of people. Often people are only seen as a bunch of blobs. Occlusions, pose variations and background clutter further compound the difficulty. In this scenario, identifying a person requires larger spatial context and semantics of the scene. But the current state-of-the-art CNN regressors for crowd counting are feedforward and use only limited spatial context to detect people. They look for local crowd patterns to regress the crowd density map, resulting in false predictions. Hence, we propose top-down feedback to correct the initial prediction of the CNN. Our architecture consists of a bottom-up CNN along with a separate top-down CNN to generate feedback. The bottom-up network, which regresses the crowd density map, has two columns of CNN with different receptive fields. Features from various layers of the bottom-up CNN are fed to the top-down network. The feedback, thus generated, is applied on the lower layers of the bottom-up network in the form of multiplicative gating. This masking weighs activations of the bottom-up network at spatial as well as feature levels to correct the density prediction. We evaluate the performance of our model on all major crowd datasets and show the effectiveness of top-down feedback.