Abstract Recent advances in image captioning have focused on enhancing accuracy by substantially increasing the dataset and model size. While conventional captioning models exhibit high performance on established metrics such as BLEU, CIDEr, and SPICE, the capability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employed contrastive learning or re-weighted the ground-truth captions. However, these approaches often overlook the relationships among objects in a similar image group (e.g., items or properties within the same album or fine-grained events). In this paper, we introduce a novel approach to enhance the distinctiveness of image captions, namely Group-based Differential Distinctive Captioning Method, which visually compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we introduce a Group-based Differential Memory Attention (GDMA) module, designed to identify and emphasize object features in an image that are uniquely distinguishable within its image group, i.e., those exhibiting low similarity with objects in other images. This mechanism ensures that such unique object features are prioritized during caption generation for the image, thereby enhancing the distinctiveness of the resulting captions. To further refine this process, we select distinctive words from the ground-truth captions to guide both the language decoder and the GDMA module. Additionally, we propose a new evaluation metric, the Distinctive Word Rate (DisWordRate), to quantitatively assess caption distinctiveness. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves state-of-the-art performance on distinctiveness while not excessively sacrificing accuracy. Moreover, the results of our user study are consistent with the quantitative evaluation and demonstrate the rationality of the new metric DisWordRate.

Convolutional neural networks (CNNs) are frequently used to analyze remote sensing images and achieve impressive progress. Limited by the receptive field size of CNNs, small objects tended to lack adequate features to obtain more accurate segmentation results. To address this problem, we introduce a novel CNN model for coarse-to-fine segmentation called C2FNet. C2FNet comprises two stages: the coarse network and the fine network. The coarse network identifies the positions and coarse segmentation outcomes of small objects in the input image. The fine network then takes a closer look at the small objects and re-segments the patches using binary segmentation. The fine network distinguishes small objects from the background to refine small object segmentation. Finally, C2FNet employs an aggregation module that merges the binary segmentation maps and coarse outcomes to obtain accurate small object segmentation. We conducted extensive experiments on three widely accepted datasets for remote sensing image segmentation, namely the ISPRS 2-D semantic labeling Potsdam, Vaihingen, and iSAID. Our approach significantly improves the performance of baseline models, achieving a 0.24%–2.83% increase in IoU per small object class on iSAID.

In the fast-growing field of Remote Sensing (RS) image analysis, the gap between massive unlabeled datasets and the ability to fully utilize these datasets for advanced RS analytics presents a significant challenge. To fill the gap, our work introduces an innovative auto-labeling framework named ALPS (Automatic Labeling for Pre-training in Segmentation), which leverages the Segment Anything Model (SAM) to predict precise pseudo-labels for RS images without necessitating prior annotations or additional prompts. The proposed pipeline significantly reduces the labor and resource demands traditionally associated with annotating RS datasets. By constructing two comprehensive pseudo-labeled RS datasets via ALPS for pre-training purposes, our approach enhances the performance of downstream tasks across various benchmarks, including iSAID and ISPRS Potsdam. Experiments demonstrate the effectiveness of our framework, showing its ability to generalize well across multiple tasks even under the scarcity of extensively annotated datasets, offering a scalable solution to automatic segmentation and annotation challenges in the field. In addition, the proposed pipeline is flexible and can be applied to medical image segmentation, remarkably increasing the performance. Note that ALPS utilizes pre-trained SAM to semi-automatically annotate RS images without additional manual annotations. Although every component in the pipeline has been well explored, integrating clustering algorithms with SAM and novel pseudo-label alignment significantly enhances RS segmentation, as an off-the-shelf tool for pre-training data preparation. Our source code is available at: https://github.com/StriveZs/ALPS.

It is challenging for crowd counting models to generalize to new scenes due to domain shifts in training and test data. Although domain adaptation approaches have made notable progress in bridging the domain gap, they require target domain data. In this paper, we propose a novel framework for cross-scene crowd counting, which unifies domain generalization and adaptation. For domain generalization, we train a model only using single-domain data and the model can be generalized to any scene with satisfying performance. Regarding domain adaptation, we use both source and target domain data to further improve the performance. We first design a generation network that diversifies the generated samples to cover the unseen target domains as much as possible by minimizing mutual information. This approach simulates training data in various domains, thereby enhancing the model's generalization ability. Then we develop a pixel-wise supervised contrastive loss function that pulls the human heads in the source images and generated images closer to each other and pushes them further away from the background. This loss helps extract a domain-invariant feature representation, thus improving the model's generalization ability. Moreover, if information about the target domain is available, our generalization method can be easily applied as an adaptation method by replacing the mutual information minimization loss with the mutual information maximization loss. This can further improve cross-scene crowd counting performance. The experimental results demonstrate the strong generalizability of our method across different datasets.

Crowd counting models in highly congested areas confront two main challenges: weak localization ability and difficulty in differentiating between foreground and background, leading to inaccurate estimations. The reason is that objects in highly congested areas are normally small and high-level features extracted by convolutional neural networks are less discriminative to represent small objects. To address these problems, we propose a learning discriminative features framework for crowd counting, which is composed of a masked feature prediction module (MPM) and a supervised pixel-level contrastive learning module (CLM). The MPM randomly masks feature vectors in the feature map and then reconstructs them, allowing the model to learn about what is present in the masked regions and improving the model's ability to localize objects in high-density regions. The CLM pulls targets close to each other and pushes them far away from background in the feature space, enabling the model to discriminate foreground objects from background. Additionally, the proposed modules can be beneficial in various computer vision tasks, such as crowd counting and object detection, where dense scenes or cluttered environments pose challenges to accurate localization. The proposed two modules are plug-and-play, incorporating the proposed modules into existing models can potentially boost their performance in these scenarios.

While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging. In this work, we release yet another sports video benchmark P 2 ANet for P ing P ong- A ction detection, which consists of 2,721 video clips collected from the broadcasting videos of professional table tennis matches in World Table Tennis Championships and Olympiads. We work with a crew of table tennis professionals and referees on a specially designed annotation toolbox to obtain fine-grained action labels (in 14 classes) for every ping-pong action that appeared in the dataset, and formulate two sets of action detection problems— action localization and action recognition . We evaluate a number of commonly seen action recognition (e.g., TSM, TSN, Video SwinTransformer, and Slowfast) and action localization models (e.g., BSN, BSN++, BMN, TCANet), using P 2 ANet for both problems, under various settings. These models can only achieve 48% area under the AR-AN curve for localization and 82% top-one accuracy for recognition since the ping-pong actions are dense with fast-moving subjects but broadcasting videos are with only 25 FPS. The results confirm that P 2 ANet is still a challenging task and can be used as a special benchmark for dense action detection from videos. We invite readers to examine our dataset by visiting the following link: https://github.com/Fred1991/P2ANET .

While Learning to Rank (LTR) models on top of transformers have been widely adopted to achieve decent performance, it is still challenging to train the model with sufficient data as only an extremely small number of query-webpage pairs could be annotated versus trillions of webpages available online and billions of web search queries everyday. In the meanwhile, industry research communities have released a number of open-source LTR datasets with well annotations but incorporating different designs of LTR features/labels (i.e., heterogeneous domains). In this work, inspired by the recent progress in pre-training transformers for performance advantages, we study the problem of pre-training LTR models using both labeled and unlabeled samples, especially we focus on the use of well-annotated samples in heterogeneous open-source LTR datasets to boost the performance of pre-training. Hereby, we propose S2phere-Semi-Supervised Pre-training with Heterogeneous LTR data strategies for LTR models using both unlabeled and labeled query-webpage pairs across heterogeneous LTR datasets. S2phere consists of a three-step approach: (1) Semi-supervised Feature Extraction Pre-training via Perturbed Contrastive Loss, (2) Cross-domain Ranker Pre-training over Heterogeneous LTR Datasets and (3) End-to-end LTR Fine-tuning via Modular Network Composition. Specifically, given an LTR model composed of a backbone (the feature extractor), a neck (the module to reason the orders) and a head (the predictor of ranking scores), S2phere uses unlabeled/labeled data from the search engine to pre-train the backbone in Step (1) via semi-supervised learning; then Step (2) incorporates multiple open-source heterogeneous LTR datasets to improve pre-training of the neck module as shared parameters of cross-domain learning; and finally, S2phere in Step (3) composes the backbone and neck with a randomly-initialized head into a whole LTR model and fine-tunes the model using search engine data with various learning strategies. Extensive experiments have been done with both offline experiments and online A/B Test on top of Baidu search engine. The comparisons against numbers of baseline algorithms confirmed the advantages of S2phere in producing high-performance LTR models for web-scale search.

Recent image captioning models are achieving impressive results based on popular metrics, i.e., BLEU, CIDEr, and SPICE. However, focusing on the most popular metrics that only consider the overlap between the generated captions and human annotation could result in using common words and phrases, which lacks distinctiveness, i.e., many similar images have the same caption. In this paper, we aim to improve the distinctiveness of image captions via comparing and reweighting with a set of similar images. First, we propose a distinctiveness metric-between-set CIDEr (CIDErBtw) to evaluate the distinctiveness of a caption with respect to those of similar images. Our metric reveals that the human annotations of each image in the MSCOCO dataset are not equivalent based on distinctiveness; however, previous works normally treat the human annotations equally during training, which could be a reason for generating less distinctive captions. In contrast, we reweight each ground-truth caption according to its distinctiveness during training. We further integrate a long-tailed weight strategy to highlight the rare words that contain more information, and captions from the similar image set are sampled as negative examples to encourage the generated sentence to be unique. Finally, extensive experiments are conducted, showing that our proposed approach significantly improves both distinctiveness (as measured by CIDErBtw and retrieval metrics) and accuracy (e.g., as measured by CIDEr) for a wide variety of image captioning baselines. These results are further confirmed through a user study.

Whilelearning to rank(LTR) has been widely used in web search to prioritize most relevant webpages among the retrieved contents subject to the input queries, the traditional LTR models fail to deliver decent performance due to two main reasons: 1) the lack of well-annotated query-webpage pairs with ranking scores to cover search queries of various popularity, and 2) ill-trained models based on a limited number of training samples with poor generalization performance. To improve the performance of LTR models, tremendous efforts have been done from above two aspects, such as enlarging training sets with pseudo-labels of ranking scores by self-training, or refining the features used for LTR through feature extraction and dimension reduction. Though LTR performance has been marginally increased, we still believe these methods could be further improved in the newly-fashioned “interpolating regime”. Specifically, instead of lowering the number of features used for LTR models, our work proposes to transform original data with random Fourier feature, so as to over-parameterize the downstream LTR models (e.g., GBRank or LightGBM) with features in ultra-high dimensionality and achieve superb generalization performance. Furthermore, rather than self-training with pseudo-labels produced by the same LTR model in a “self-tuned” fashion, the proposed method incorporates the diversity of prediction results between the listwise and pointwise LTR models while co-training both models with a cyclic labeling-prediction pipeline in a “ping-pong” manner. We deploy the proposedCo-trained andOver-parameterizedLTRsystemCOLTRat Baidu search and evaluateCOLTRwith a large number of baseline methods. The results show thatCOLTRcould achieve$\Delta NDCG_{4}$= 3.64%$\sim$4.92%, compared to baselines, under various ratios of labeled samples. We also conduct a 7-day A/B Test using the realistic web traffics of Baidu Search, where we can still observe significant performance improvement around$\Delta NDCG_{4}$= 0.17%$\sim$0.92% in real-world applications.COLTRperforms consistently both in online and offline experiments.

To understand human behaviors, action recognition based on videos is a common approach. Compared with image-based action recognition, videos provide much more information, reducing the ambiguity of actions. In the last decade, many works focus on datasets, novel models and learning approaches have improved video action recognition to a higher level. However, there are challenges and unsolved problems, in particular in sports analytics where data collection and labeling are more sophisticated, requiring people with domain knowledge and even sport professionals to annotate data. In addition, the actions could be extremely fast and it becomes difficult to recognize them. Moreover, in team sports like football and basketball, one action could involve multiple players, and to correctly recognize them, we need to analyze all players, which is relatively complicated. In this paper, we present a survey on video action recognition for sports analytics. We introduce more than ten types of sports, including team sports, such as football, basketball, volleyball, hockey and individual sports, such as figure skating, gymnastics, table tennis, tennis, diving and badminton. Then we compare numerous existing frameworks for sports analysis to present status quo of video action recognition in both team sports and individual sports. Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.

While recommender systems have been ubiquitously used in digital marketing and online business development, the conversions of online advertising for mobile apps installation and activation sometimes are far from satisfactory, due to the lack of feedback from App-related activities, leading to a poor record of Return on Investment (RoI). Though the advertisers, e.g., App operators and App Store, are granted to log users’ app-related activities such as installation, activation, usages, and preferences per the agreement, they usually limit the access to such data from advertisement publishers, due to the privacy concerns. To improve conversions of online advertising under privacy controls, we proposeFeynman—afederated learning-based advertising platform for ecosystems-orientedmobileapps recommendation.Feynmanaims at improving the RoI of mobile app recommendation from an ecosystem's perspective, i.e., per investment in advertising an app (Goal. 1) increasing the number of new installs/users of the app, and then (Goal. 2) increasing the number of new active users (preferably with frequent in-app purchase activities). Incorporating with a federated computing platform,Feynmanleverages users’ records stored in advertisers to refine the pool of targeting users for ads distribution, and jointly builds the predictive models for users’ purchase activities forecasting using features from the Ads publisher and the advertiser. With refined target pools and more accurate models,Feynmanhas successfully helped several mobile apps in China by attracting more than 100 million users to further enlarge their user populations and revenues from in-app purchases. Note that rather than proposing new techniques for federated learning, the design ofFeynmandedicates to show its promising performance in the industrial practices of advertising using federated computing and privacy protected strategies. In three cases that we report in this paper,Feynmanoutperforms the state-of-the-art plans in terms of several key measurements, including Click-Through Rates (CTR), Conversion Rate (CVR), Cost per Action (CPA), and Non-targeting User Hit-Rates (NTHR).

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined view generation methods, e.g., node drop or edge perturbation, which usually cannot adapt to input data or preserve the original semantic structures well. To address this issue, we propose a novel framework named Automated Graph Contrastive Learning (AutoGCL) in this paper. Specifically, AutoGCL employs a set of learnable graph view generators orchestrated by an auto augmentation strategy, where every graph view generator learns a probability distribution of graphs conditioned by the input. While the graph view generators in AutoGCL preserve the most representative structures of the original graph in generation of every contrastive sample, the auto augmentation learns policies to introduce adequate augmentation variances in the whole contrastive learning procedure. Furthermore, AutoGCL adopts a joint training strategy to train the learnable view generators, the graph encoder, and the classifier in an end-to-end manner, resulting in topological heterogeneity yet semantic similarity in the generation of contrastive samples. Extensive experiments on semi-supervised learning, unsupervised learning, and transfer learning demonstrate the superiority of our AutoGCL framework over the state-of-the-arts in graph contrastive learning. In addition, the visualization results further confirm that the learnable view generators can deliver more compact and semantically meaningful contrastive samples compared against the existing view generation methods. Our code is available at https://github.com/Somedaywilldo/AutoGCL.

Arbitrary image style transfer is a challenging task which aims to stylize a content image conditioned on arbitrary style images. In this task the feature-level content-style transformation plays a vital role for proper fusion of features. Existing feature transformation algorithms often suffer from loss of content or style details, non-natural stroke patterns, and unstable training. To mitigate these issues, this paper proposes a new feature-level style transformation technique, named Style Projection, for parameter-free, fast, and effective content-style transformation. This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs. Extensive qualitative analysis, quantitative evaluation, and user study have demonstrated the effectiveness and efficiency of the proposed methods.

Crowd counting is an essential topic in computer vision due to its practical usage in surveillance systems. The typical design of crowd counting algorithms is divided into two steps. First, the ground-truth density maps of crowd images are generated from the ground-truth dot maps (density map generation), e.g., by convolving with a Gaussian kernel. Second, deep learning models are designed to predict a density map from an input image (density map estimation). The density map based counting methods that incorporate density map as the intermediate representation have improved counting performance dramatically. However, in the sense of end-to-end training, the hand-crafted methods used for generating the density maps may not be optimal for the particular network or dataset used. To address this issue, we propose an adaptive density map generator, which takes the annotation dot map as input, and learns a density map representation for a counter. The counter and generator are trained jointly within an end-to-end framework. We also show that the proposed framework can be applied to general dense object counting tasks. Extensive experiments are conducted on 10 datasets for 3 applications: crowd counting, vehicle counting, and general object counting. The experiment results on these datasets confirm the effectiveness of the proposed learnable density map representations.

Diversity is one of the most important properties in image captioning, as it reflects various expressions of important concepts presented in an image. However, the most popular metrics cannot well evaluate the diversity of multiple captions. In this paper, we first propose a metric to measure the diversity of a set of captions, which is derived from latent semantic analysis (LSA), and then kernelize LSA using CIDEr (R. Vedantam et al., 2015) similarity. Compared with mBLEU (R. Shetty et al., 2017), our proposed diversity metrics show a relatively strong correlation to human evaluation. We conduct extensive experiments, finding there is a large gap between the performance of the current state-of-the-art models and human annotations considering both diversity and accuracy; the models that aim to generate captions with higher CIDEr scores normally obtain lower diversity scores, which generally learn to describe images using common words. To bridge this "diversity" gap, we consider several methods for training caption models to generate diverse captions. First, we show that balancing the cross-entropy loss and CIDEr reward in reinforcement learning during training can effectively control the tradeoff between diversity and accuracy of the generated captions. Second, we develop approaches that directly optimize our diversity metric and CIDEr score using reinforcement learning. These proposed approaches using reinforcement learning (RL) can be unified into a self-critical (S. J. Rennie et al., 2017) framework with new RL baselines. Third, we combine accuracy and diversity into a single measure using an ensemble matrix, and then maximize the determinant of the ensemble matrix via reinforcement learning to boost diversity and accuracy, which outperforms its counterparts on the oracle test. Finally, inspired by determinantal point processes (DPP), we develop a DPP selection algorithm to select a subset of captions from a large number of candidate captions. The experimental results show that maximizing the determinant of the ensemble matrix outperforms other methods considerably improving diversity and accuracy.

Describing images using natural language is widely known as image captioning, which has made consistent progress due to the development of computer vision and natural language generation techniques. Though conventional captioning models achieve high accuracy based on popular metrics, i.e., BLEU, CIDEr, and SPICE, the ability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employ contrastive learning or re-weighted the ground-truth captions, which focuses on one single input image. However, the relationships between objects in a similar image group (e.g., items or properties within the same album or fine-grained events) are neglected. In this paper, we improve the distinctiveness of image captions using a Group-based Distinctive Captioning Model (GdisCap), which compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we propose a group-based memory attention (GMA) module, which stores object features that are unique among the image group (i.e., with low similarity to objects in other images). These unique object features are highlighted when generating captions, resulting in more distinctive captions. Furthermore, the distinctive words in the ground-truth captions are selected to supervise the language decoder and GMA. Finally, we propose a new evaluation metric, distinctive word rate (DisWordRate) to measure the distinctiveness of captions. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves the state-of-the-art performance on both accuracy and distinctiveness. Results of a user study agree with the quantitative evaluation and demonstrate the rationality of the new metric DisWordRate.

Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e.g., appearance, pose, foreground, background, local details, global structures, etc. In this paper, we present a novel end-to-end framework to generate realistic person images based on given person poses and appearances. The core of our framework is a novel generator called Appearance-aware Pose Stylizer (APS) which generates human images by coupling the target pose with the conditioned person appearance progressively. The framework is highly flexible and controllable by effectively decoupling various complex person image factors in the encoding phase, followed by re-coupling them in the decoding phase. In addition, we present a new normalization method named adaptive patch normalization, which enables region-specific normalization and shows a good performance when adopted in person image generation model. Experiments on two benchmark datasets show that our method is capable of generating visually appealing and realistic-looking results using arbitrary image and pose inputs.

Recently, the state-of-the-art models for image captioning have overtaken human performance based on the most popular metrics, such as BLEU, METEOR, ROUGE and CIDEr. Does this mean we have solved the task of image captioning The above metrics only measure the similarity of the generated caption to the human annotations, which reflects its accuracy. However, an image contains many concepts and multiple levels of detail, and thus there is a variety of captions that express different concepts and details that might be interesting for different humans. Therefore only evaluating accuracy is not sufficient for measuring the performance of captioning models --- the diversity of the generated captions should also be considered. In this paper, we proposed a new metric for measuring the diversity of image captions, which is derived from latent semantic analysis and kernelized to use CIDEr similarity. We conduct extensive experiments to re-evaluate recent captioning models in the context of both diversity and accuracy. We find that there is still a large gap between the model and human performance in terms of both accuracy and diversity, and the models that have optimized accuracy (CIDEr) have low diversity. We also show that balancing the cross-entropy loss and CIDEr reward in reinforcement learning during training can effectively control the tradeoff between diversity and accuracy of the generated captions.

Harmony search algorithm (HS) is a meta-heuristic algorithm which is inspired by a process involving musical improvisation. It is a stochastic optimization technique, which is similar to genetic algorithms (GAs) and particle swarm optimizers (PSOs). And it has been widely applied in order to solve many complex optimization problems, including continuous and discrete problems, such as structure design, function optimization, controller design. In this paper, two improved harmony search algorithms based on tournament selection operator (THSs) are developed. With tournament selection operator being employed as a significant improvement to the performance of the original algorithm, the THSs were then applied to function optimization problems. The results of the experiment show that THSs is capable of finding better solutions when compared to HS.