Search

As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality, and its key challenge is to measure the semantic similarity across different modalities. Although significant progress has been achieved, existing approaches typically suffer from two major limitations: (1) It hurts the accuracy of the representation by directly exploiting the bottom-up attention based region-level features where each region is equally treated. (2) It limits the scale of negative sample pairs by employing the mini-batch based end-to-end training mechanism. To address these limitations, we propose a Unified Semantic Enhancement Momentum Contrastive Learning (USER) method for ITR. Specifically, we delicately design two simple but effective Global representation based Semantic Enhancement (GSE) modules. One learns the global representation via the self-attention algorithm, noted as Self-Guided Enhancement (SGE) module. The other module benefits from the pre-trained CLIP module, which provides a novel scheme to exploit and transfer the knowledge from an off-the-shelf model, noted as CLIP-Guided Enhancement (CGE) module. Moreover, we incorporate the training mechanism of MoCo into ITR, in which two dynamic queues are employed to enrich and enlarge the scale of negative sample pairs. Meanwhile, a Unified Training Objective (UTO) is developed to learn from mini-batch based and dynamic queue based samples. Extensive experiments on the benchmark MSCOCO and Flickr30K datasets demonstrate the superiority of both retrieval accuracy and inference efficiency. For instance, compared with the existing best method NAAF, the metric R@1 of our USER on the MSCOCO 5K Testing set is improved by 5% and 2.4% on caption retrieval and image retrieval without any external knowledge or pre-trained model while enjoying over 60 times faster inference speed. Our source code will be released at https://github.com/zhangy0822/USER. [ABSTRACT FROM AUTHOR]

Few-shot learning (FSL) for human–object interaction (HOI) aims at recognizing various relationships between human actions and surrounding objects only from a few samples. It is a challenging vision task, in which the diversity and interactivity of human actions result in great difficulty to learn an adaptive classifier to catch ambiguous interclass information. Therefore, traditional FSL methods usually perform unsatisfactorily in complex HOI scenes. To this end, we propose dynamic graph-in-graph networks (DGIG-Net), a novel graph prototypes framework to learn a dynamic metric space by embedding a visual subgraph to a task-oriented cross-modal graph for few-shot HOI. Specifically, we first build a knowledge reconstruction graph to learn latent representations for HOI categories by reconstructing the relationship among visual features, which generates visual representations under the category distribution of every task. Then, a dynamic relation graph integrates both reconstructible visual nodes and dynamic task-oriented semantic information to explore a graph metric space for HOI class prototypes, which applies the discriminative information from the similarities among actions or objects. We validate DGIG-Net on multiple benchmark datasets, on which it largely outperforms existing FSL approaches and achieves state-of-the-art results. [ABSTRACT FROM AUTHOR]

Visual tracking is a very critical issue in computer vision and video processing. For Discriminative Correlation Filter (DCF)-based tracking methods, it is very essential and meaningful to adaptively incorporate reliable target and surrounding information from video frames. However, most existing DCF-based trackers solely rely on pre-defined and fixed constraints such as a binary mask or quadratic function-based regularization to improve the discrimination. Unfortunately, such attempts fail to adjust the constraints according to the change of tracking circumstance in the video sequence, and thus lead to the lack of reliability of learned filters. To mitigate these problems, we present a novel DCF-based tracking method that introduces an adaptive target-and-surrounding soft mask (ATSM) into the learning formula. The adaptive soft mask that is represented by float numbers contains the detail information for both target region and its surrounding information: first, for the background area, it introduces meaningful background information and suppressing uninformative one; second, for the target area inside the bounding box, it helps to focus on the reliable area and repress the rapidly changing area; third, the target-and-surrounding soft mask is adaptively adjusted based on the variations of the target and its surrounding during the tracking process. By jointly modeling the filter and the adaptive soft mask, our ATSM tracker achieves an efficient integration of meaningful information of both foreground and background and performs favorably against state-of-the-art algorithms on seven well-known benchmarks. [ABSTRACT FROM AUTHOR]

Stego-images are often contaminated by interchannel noise or active noise attack when communicating on the Web. And it is challenging to restore embedded image from corrupted stego-image. This paper studies a kNN-bit approximation algorithm to remove noises in embedded image. The proposed algorithm distinguishes reliable bits from extracted bits, and estimates pixel values by keeping reliable bits unchanged and correcting unreliable bits. Specifically, the 8th (highest) unreliable bit of a pixel can be approximated with its nearest neighbor pixels. And then, if an unreliable bit locates at any one of the $5^{th}\sim 7^{th}$ 5 t h ∼ 7 t h bits of a pixel, it is adjusted with two nearest neighbors of the pixel, where the pixel is in-between these two nearest neighbors. Finally, for other unreliable bits, each one is approximated by the maximum and minimum possible values of nearest neighbors of its pixel. We conduct experiments for illustrating the efficiency, and demonstrate that the proposed algorithm can recover the embedded images with good visual quality from corrupted stego-images. [ABSTRACT FROM AUTHOR]

Extreme instance imbalance among categories and combinatorial explosion make the recognition of Human-Object Interaction (HOI) a challenging task. Few studies have addressed both challenges directly. Motivated by the success of few-shot learning that learns a robust model from a few instances, we formulate HOI as a few-shot task in a meta-learning framework to alleviate the above challenges. Due to the fact that the intrinsical characteristic of HOI is diverse and interactive, we propose a Semantic-guided Attentive Prototypes Network (SAPNet) framework to learn a semantic-guided metric space where HOI recognition can be performed by computing distances to attentive prototypes of each class. Specifically, the model generates attentive prototypes guided by the category names of actions and objects, which highlight the commonalities of images from the same class in HOI. In addition, we design two alternative prototypes calculation methods, i.e., Prototypes Shift (PS) approach and Hallucinatory Graph Prototypes (HGP) approach, which explore to learn a suitable category prototypes representations in HOI. Finally, in order to realize the task of few-shot HOI, we reorganize 2 HOI benchmark datasets with 2 split strategies, i.e., HICO-NN, TUHOI-NN, HICO-NF, and TUHOI-NF. Extensive experimental results on these datasets have demonstrated the effectiveness of our proposed SAPNet approach. [ABSTRACT FROM AUTHOR]

To benefit the skin care, this paper aims to design an automatic and effective visual analysis framework, with the expectation of recognizing the skin disease from a given image conveying the disease affected surface. This task is nontrivial, since it is hard to collect sufficient well-labeled samples. To address such problem, we present a novel transfer learning model, which is able to incorporate external knowledge obtained from the rich and relevant Web images contributed by grassroots. In particular, we first construct a target domain by crawling a small set of images from vertical and professional dermatological websites. We then construct a source domain by collecting a large set of skin disease related images from commercial search engines. To reinforce the learning performance in the target domain, we initially build a learning model in the target domain, and then seamlessly leverage the training samples in the source domain to enhance this learning model. The distribution gap between these two domains are bridged by a linear combination of Gaussian kernels. Instead of training models with low-level features, we resort to deep models to learn the succinct, invariant, and high-level image representations. Different from previous efforts that focus on a few types of skin diseases with a small and confidential set of images generated from hospitals, this paper targets at thousands of commonly seen skin diseases with publicly accessible Web images. Hence the proposed model is easily repeatable by other researchers and extendable to other disease types. Extensive experiments on a real-world dataset have demonstrated the superiority of our proposed method over the state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Sufficient training examples are the fundamental requirement for most of the learning tasks. However, collecting well-labelled training examples is costly. Inspired by Zero-shot Learning (ZSL) that can make use of visual attributes or natural language semantics as an intermediate level clue to associate low-level features with high-level classes, in a novel extension of this idea, we aim to synthesise training data for novel classes using only semantic attributes. Despite the simplicity of this idea, there are several challenges. First, how to prevent the synthesised data from over-fitting to training classes? Second, how to guarantee the synthesised data is discriminative for ZSL tasks? Third, we observe that only a few dimensions of the learnt features gain high variances whereas most of the remaining dimensions are not informative. Thus, the question is how to make the concentrated information diffuse to most of the dimensions of synthesised data. To address the above issues, we propose a novel embedding algorithm named Unseen Visual Data Synthesis (UVDS) that projects semantic features to the high-dimensional visual feature space. Two main techniques are introduced in our proposed algorithm. (1) We introduce a latent embedding space which aims to reconcile the structural difference between the visual and semantic spaces, meanwhile preserve the local structure. (2) We propose a novel Diffusion Regularisation (DR) that explicitly forces the variances to diffuse over most dimensions of the synthesised data. By an orthogonal rotation (more precisely, an orthogonal transformation), DR can remove the redundant correlated attributes and further alleviate the over-fitting problem. On four benchmark datasets, we demonstrate the benefit of using synthesised unseen data for zero-shot learning. Extensive experimental results suggest that our proposed approach significantly outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Hashing methods are effective in generating compact binary signatures for images and videos. This paper addresses an important open issue in the literature, i.e., how to learn compact hash codes by enhancing the complementarity among different hash functions. Most of prior studies solve this problem either by adopting time-consuming sequential learning algorithms or by generating the hash functions which are subject to some deliberately-designed constraints (e.g., enforcing hash functions orthogonal to one another). We analyze the drawbacks of past works and propose a new solution to this problem. Our idea is to decompose the feature space into a subspace shared by all hash functions and its complementary subspace. On one hand, the shared subspace, corresponding to the common structure across different hash functions, conveys most relevant information for the hashing task. Similar to data de-noising, irrelevant information is explicitly suppressed during hash function generation. On the other hand, in case that the complementary subspace also contains useful information for specific hash functions, the final form of our proposed hashing scheme is a compromise between these two kinds of subspaces. To make hash functions not only preserve the local neighborhood structure but also capture the global cluster distribution of the whole data, an objective function incorporating spectral embedding loss, binary quantization loss, and shared subspace contribution is introduced to guide the hash function learning. We propose an efficient alternating optimization method to simultaneously learn both the shared structure and the hash functions. Experimental results on three well-known benchmarks CIFAR-10, NUS-WIDE, and a-TRECVID demonstrate that our approach significantly outperforms state-of-the-art hashing methods. [ABSTRACT FROM PUBLISHER]

We present a framework for image classification that extends beyond the window sampling of fixed spatial pyramids and is supported by a new learning algorithm. Based on the observation that fixed spatial pyramids sample a rather limited subset of the possible image windows, we propose a method that accounts for a comprehensive set of windows densely sampled over location, size, and aspect ratio. A concise high-level image feature is derived to effectively deal with this large set of windows, and this higher level of abstraction offers both efficient handling of the dense samples and reduced sensitivity to misalignment. In addition to dense window sampling, we introduce generalized adaptive \ell p -norm multiple kernel learning (GA-MKL) to learn a robust classifier based on multiple base kernels constructed from the new image features and multiple sets of prelearned classifiers from other classes. With GA-MKL, multiple levels of image features are effectively fused, and information is shared among different classifiers. Extensive evaluation on benchmark datasets for object recognition (Caltech256 and Caltech101) and scene recognition (15Scenes) demonstrate that the proposed method outperforms the state-of-the-art under a broad range of settings. [ABSTRACT FROM PUBLISHER]

The biologically inspired model (BIM) proposed by Serre presents a promising solution to object categorization. It emulates the process of object recognition in primates' visual cortex by constructing a set of scale- and position-tolerant features whose properties are similar to those of the cells along the ventral stream of visual cortex. However, BIM has potential to be further improved in two aspects: mismatch by dense input and randomly feature selection due to the feedforward framework. To solve or alleviate these limitations, we develop an enhanced BIM (EBIM) in terms of the following two aspects: 1) removing uninformative inputs by imposing sparsity constraints, 2) apply a feedback loop to middle level feature selection. Each aspect is motivated by relevant psychophysical research findings. To show the effectiveness of the EBIM, we apply it to object categorization and conduct empirical studies on four computer vision data sets. Experimental results demonstrate that the EBIM outperforms the BIM and is comparable to state-of-the-art approaches in terms of accuracy. Moreover, the new system is about 20 times faster than the BIM. [ABSTRACT FROM AUTHOR]