Gang Yang

Xirong Li, Chaoxi Xu, Xiaoxu Wang et al.

This paper contributes to cross-lingual image annotation and retrieval in terms of data and baseline methods. We propose COCO-CN, a novel dataset enriching MS-COCO with manually written Chinese sentences and tags. For more effective annotation acquisition, we develop a recommendation-assisted collective annotation system, automatically providing an annotator with several tags and sentences deemed to be relevant with respect to the pictorial content. Having 20,342 images annotated with 27,218 Chinese sentences and 70,993 tags, COCO-CN is currently the largest Chinese-English dataset that provides a unified and challenging platform for cross-lingual image tagging, captioning and retrieval. We develop conceptually simple yet effective methods per task for learning from cross-lingual resources. Extensive experiments on the three tasks justify the viability of the proposed dataset and methods. Data and code are publicly available at https://github.com/li-xirong/coco-cn

Xirong Li, Fangming Zhou, Chaoxi Xu et al.

Retrieving unlabeled videos by textual queries, known as Ad-hoc Video Search (AVS), is a core theme in multimedia data management and retrieval. The success of AVS counts on cross-modal representation learning that encodes both query sentences and videos into common spaces for semantic similarity computation. Inspired by the initial success of previously few works in combining multiple sentence encoders, this paper takes a step forward by developing a new and general method for effectively exploiting diverse sentence encoders. The novelty of the proposed method, which we term Sentence Encoder Assembly (SEA), is two-fold. First, different from prior art that use only a single common space, SEA supports text-video matching in multiple encoder-specific common spaces. Such a property prevents the matching from being dominated by a specific encoder that produces an encoding vector much longer than other encoders. Second, in order to explore complementarities among the individual common spaces, we propose multi-space multi-loss learning. As extensive experiments on four benchmarks (MSR-VTT, TRECVID AVS 2016-2019, TGIF and MSVD) show, SEA surpasses the state-of-the-art. In addition, SEA is extremely ease to implement. All this makes SEA an appealing solution for AVS and promising for continuously advancing the task by harvesting new sentence encoders.

Jianfeng Dong, Xirong Li, Chaoxi Xu et al.

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Our novelty is two-fold. First, different from prior art that resorts to a specific single-level encoder, the proposed network performs multi-level encoding that represents the rich content of both modalities in a coarse-to-fine fashion. Second, different from a conventional common space learning algorithm which is either concept based or latent space based, we introduce hybrid space learning which combines the high performance of the latent space and the good interpretability of the concept space. Dual encoding is conceptually simple, practically effective and end-to-end trained with hybrid space learning. Extensive experiments on four challenging video datasets show the viability of the new method.

Fei Ding, Gang Yang, Jinlu Liu et al.

The medical image is characterized by the inter-class indistinction, high variability, and noise, where the recognition of pixels is challenging. Unlike previous self-attention based methods that capture context information from one level, we reformulate the self-attention mechanism from the view of the high-order graph and propose a novel method, namely Hierarchical Attention Network (HANet), to address the problem of medical image segmentation. Concretely, an HA module embedded in the HANet captures context information from neighbors of multiple levels, where these neighbors are extracted from the high-order graph. In the high-order graph, there will be an edge between two nodes only if the correlation between them is high enough, which naturally reduces the noisy attention information caused by the inter-class indistinction. The proposed HA module is robust to the variance of input and can be flexibly inserted into the existing convolution neural networks. We conduct experiments on three medical image segmentation tasks including optic disc/cup segmentation, blood vessel segmentation, and lung segmentation. Extensive results show our method is more effective and robust than the existing state-of-the-art methods.

Gang Yang, Jinlu Liu, Xirong Li

Zero-shot learning (ZSL) which aims to recognize unseen classes with no labeled training sample, efficiently tackles the problem of missing labeled data in image retrieval. Nowadays there are mainly two types of popular methods for ZSL to recognize images of unseen classes: probabilistic reasoning and feature projection. Different from these existing types of methods, we propose a new method: sample construction to deal with the problem of ZSL. Our proposed method, called Imagination Based Sample Construction (IBSC), innovatively constructs image samples of target classes in feature space by mimicking human associative cognition process. Based on an association between attribute and feature, target samples are constructed from different parts of various samples. Furthermore, dissimilarity representation is employed to select high-quality constructed samples which are used as labeled data to train a specific classifier for those unseen classes. In this way, zero-shot learning is turned into a supervised learning problem. As far as we know, it is the first work to construct samples for ZSL thus, our work is viewed as a baseline for future sample construction methods. Experiments on four benchmark datasets show the superiority of our proposed method.

Yu Zeng, Huchuan Lu, Ali Borji et al.

We propose a novel unsupervised game-theoretic salient object detection algorithm that does not require labeled training data. First, saliency detection problem is formulated as a non-cooperative game, hereinafter referred to as Saliency Game, in which image regions are players who choose to be "background" or "foreground" as their pure strategies. A payoff function is constructed by exploiting multiple cues and combining complementary features. Saliency maps are generated according to each region's strategy in the Nash equilibrium of the proposed Saliency Game. Second, we explore the complementary relationship between color and deep features and propose an Iterative Random Walk algorithm to combine saliency maps produced by the Saliency Game using different features. Iterative random walk allows sharing information across feature spaces, and detecting objects that are otherwise very hard to detect. Extensive experiments over 6 challenging datasets demonstrate the superiority of our proposed unsupervised algorithm compared to several state of the art supervised algorithms.

Xixi He, Xirong Li, Gang Yang et al.

Not all tags are relevant to an image, and the number of relevant tags is image-dependent. Although many methods have been proposed for image auto-annotation, the question of how to determine the number of tags to be selected per image remains open. The main challenge is that for a large tag vocabulary, there is often a lack of ground truth data for acquiring optimal cutoff thresholds per tag. In contrast to previous works that pre-specify the number of tags to be selected, we propose in this paper adaptive tag selection. The key insight is to divide the vocabulary into two disjoint subsets, namely a seen set consisting of tags having ground truth available for optimizing their thresholds and a novel set consisting of tags without any ground truth. Such a division allows us to estimate how many tags shall be selected from the novel set according to the tags that have been selected from the seen set. The effectiveness of the proposed method is justified by our participation in the ImageCLEF 2014 image annotation task. On a set of 2,065 test images with ground truth available for 207 tags, the benchmark evaluation shows that compared to the popular top-$k$ strategy which obtains an F-score of 0.122, adaptive tag selection achieves a higher F-score of 0.223. Moreover, by treating the underlying image annotation system as a black box, the new method can be used as an easy plug-in to boost the performance of existing systems.