Hao Wang

Yining Ye, Xin Cong, Shizuo Tian et al. · tencent-ai

From ancient water wheels to robotic process automation (RPA), automation technology has evolved throughout history to liberate human beings from arduous tasks. Yet, RPA struggles with tasks needing human-like intelligence, especially in elaborate design of workflow construction and dynamic decision-making in workflow execution. As Large Language Models (LLMs) have emerged human-like intelligence, this paper introduces Agentic Process Automation (APA), a groundbreaking automation paradigm using LLM-based agents for advanced automation by offloading the human labor to agents associated with construction and execution. We then instantiate ProAgent, an LLM-based agent designed to craft workflows from human instructions and make intricate decisions by coordinating specialized agents. Empirical experiments are conducted to detail its construction and execution procedure of workflow, showcasing the feasibility of APA, unveiling the possibility of a new paradigm of automation driven by agents. Our code is public at https://github.com/OpenBMB/ProAgent.

Hao Wang, Guosheng Lin, Ana García del Molino et al.

In this paper we present a novel multi-attribute face manipulation method based on textual descriptions. Previous text-based image editing methods either require test-time optimization for each individual image or are restricted to single attribute editing. Extending these methods to multi-attribute face image editing scenarios will introduce undesired excessive attribute change, e.g., text-relevant attributes are overly manipulated and text-irrelevant attributes are also changed. In order to address these challenges and achieve natural editing over multiple face attributes, we propose a new decoupling training scheme where we use group sampling to get text segments from same attribute categories, instead of whole complex sentences. Further, to preserve other existing face attributes, we encourage the model to edit the latent code of each attribute separately via an entropy constraint. During the inference phase, our model is able to edit new face images without any test-time optimization, even from complex textual prompts. We show extensive experiments and analysis to demonstrate the efficacy of our method, which generates natural manipulated faces with minimal text-irrelevant attribute editing. Code and pre-trained model are available at https://github.com/hwang1996/ManiCLIP.

Shiwei Wu, Weidong He, Tong Xu et al.

Affordance-centric Question-driven Task Completion for Egocentric Assistant(AQTC) is a novel task which helps AI assistant learn from instructional videos and scripts and guide the user step-by-step. In this paper, we deal with the AQTC via a two-stage Function-centric approach, which consists of Question2Function Module to ground the question with the related function and Function2Answer Module to predict the action based on the historical steps. We evaluated several possible solutions in each module and obtained significant gains compared to the given baselines. Our code is available at \url{https://github.com/starsholic/LOVEU-CVPR22-AQTC}.

Hao Wang, Guosheng Lin, Steven C. H. Hoi et al.

This paper investigates an open research problem of generating text-image pairs to improve the training of fine-grained image-to-text cross-modal retrieval task, and proposes a novel framework for paired data augmentation by uncovering the hidden semantic information of StyleGAN2 model. Specifically, we first train a StyleGAN2 model on the given dataset. We then project the real images back to the latent space of StyleGAN2 to obtain the latent codes. To make the generated images manipulatable, we further introduce a latent space alignment module to learn the alignment between StyleGAN2 latent codes and the corresponding textual caption features. When we do online paired data augmentation, we first generate augmented text through random token replacement, then pass the augmented text into the latent space alignment module to output the latent codes, which are finally fed to StyleGAN2 to generate the augmented images. We evaluate the efficacy of our augmented data approach on two public cross-modal retrieval datasets, in which the promising experimental results demonstrate the augmented text-image pair data can be trained together with the original data to boost the image-to-text cross-modal retrieval performance.

Jiacheng Wei, Hao Wang, Jiashi Feng et al.

In this paper, we investigate an open research task of generating controllable 3D textured shapes from the given textual descriptions. Previous works either require ground truth caption labeling or extensive optimization time. To resolve these issues, we present a novel framework, TAPS3D, to train a text-guided 3D shape generator with pseudo captions. Specifically, based on rendered 2D images, we retrieve relevant words from the CLIP vocabulary and construct pseudo captions using templates. Our constructed captions provide high-level semantic supervision for generated 3D shapes. Further, in order to produce fine-grained textures and increase geometry diversity, we propose to adopt low-level image regularization to enable fake-rendered images to align with the real ones. During the inference phase, our proposed model can generate 3D textured shapes from the given text without any additional optimization. We conduct extensive experiments to analyze each of our proposed components and show the efficacy of our framework in generating high-fidelity 3D textured and text-relevant shapes.

Hao Wang, Wenhao Shen, Guosheng Lin et al.

In this paper, we investigate an open research task of generating 3D cartoon face shapes from single 2D GAN generated human faces and without 3D supervision, where we can also manipulate the facial expressions of the 3D shapes. To this end, we discover the semantic meanings of StyleGAN latent space, such that we are able to produce face images of various expressions, poses, and lighting conditions by controlling the latent codes. Specifically, we first finetune the pretrained StyleGAN face model on the cartoon datasets. By feeding the same latent codes to face and cartoon generation models, we aim to realize the translation from 2D human face images to cartoon styled avatars. We then discover semantic directions of the GAN latent space, in an attempt to change the facial expressions while preserving the original identity. As we do not have any 3D annotations for cartoon faces, we manipulate the latent codes to generate images with different poses and lighting conditions, such that we can reconstruct the 3D cartoon face shapes. We validate the efficacy of our method on three cartoon datasets qualitatively and quantitatively.

Yunfan Zhang, Hao Wang, Guosheng Lin et al.

This paper investigates an open research task of reconstructing and generating 3D point clouds. Most existing works of 3D generative models directly take the Gaussian prior as input for the decoder to generate 3D point clouds, which fail to learn disentangled latent codes, leading noisy interpolated results. Most of the GAN-based models fail to discriminate the local geometries, resulting in the point clouds generated not evenly distributed at the object surface, hence degrading the point cloud generation quality. Moreover, prevailing methods adopt computation-intensive frameworks, such as flow-based models and Markov chains, which take plenty of time and resources in the training phase. To resolve these limitations, this paper proposes a unified style-aware network architecture combining both point-wise distance loss and adversarial loss, StarNet which is able to reconstruct and generate high-fidelity and even 3D point clouds using a mapping network that can effectively disentangle the Gaussian prior from input's high-level attributes in the mapped latent space to generate realistic interpolated objects. Experimental results demonstrate that our framework achieves comparable state-of-the-art performance on various metrics in the point cloud reconstruction and generation tasks, but is more lightweight in model size, requires much fewer parameters and less time for model training.

Hao Wang, Bin Guo, Yating Zeng et al.

The intelligent dialogue system, aiming at communicating with humans harmoniously with natural language, is brilliant for promoting the advancement of human-machine interaction in the era of artificial intelligence. With the gradually complex human-computer interaction requirements (e.g., multimodal inputs, time sensitivity), it is difficult for traditional text-based dialogue system to meet the demands for more vivid and convenient interaction. Consequently, Visual Context Augmented Dialogue System (VAD), which has the potential to communicate with humans by perceiving and understanding multimodal information (i.e., visual context in images or videos, textual dialogue history), has become a predominant research paradigm. Benefiting from the consistency and complementarity between visual and textual context, VAD possesses the potential to generate engaging and context-aware responses. For depicting the development of VAD, we first characterize the concepts and unique features of VAD, and then present its generic system architecture to illustrate the system workflow. Subsequently, several research challenges and representative works are detailed investigated, followed by the summary of authoritative benchmarks. We conclude this paper by putting forward some open issues and promising research trends for VAD, e.g., the cognitive mechanisms of human-machine dialogue under cross-modal dialogue context, and knowledge-enhanced cross-modal semantic interaction.

Sirui Zhao, Huaying Tang, Xinglong Mao et al.

One of the most important subconscious reactions, micro-expression (ME), is a spontaneous, subtle, and transient facial expression that reveals human beings' genuine emotion. Therefore, automatically recognizing ME (MER) is becoming increasingly crucial in the field of affective computing, providing essential technical support for lie detection, clinical psychological diagnosis, and public safety. However, the ME data scarcity has severely hindered the development of advanced data-driven MER models. Despite the recent efforts by several spontaneous ME databases to alleviate this problem, there is still a lack of sufficient data. Hence, in this paper, we overcome the ME data scarcity problem by collecting and annotating a dynamic spontaneous ME database with the largest current ME data scale called DFME (Dynamic Facial Micro-expressions). Specifically, the DFME database contains 7,526 well-labeled ME videos spanning multiple high frame rates, elicited by 671 participants and annotated by more than 20 professional annotators over three years. Furthermore, we comprehensively verify the created DFME, including using influential spatiotemporal video feature learning models and MER models as baselines, and conduct emotion classification and ME action unit classification experiments. The experimental results demonstrate that the DFME database can facilitate research in automatic MER, and provide a new benchmark for this field. DFME will be published via https://mea-lab-421.github.io.

Shi Hanyu, Wei Jiacheng, Wang Hao et al.

LiDAR-based 3D scene perception is a fundamental and important task for autonomous driving. Most state-of-the-art methods on LiDAR-based 3D recognition tasks focus on single frame 3D point cloud data, and the temporal information is ignored in those methods. We argue that the temporal information across the frames provides crucial knowledge for 3D scene perceptions, especially in the driving scenario. In this paper, we focus on spatial and temporal variations to better explore the temporal information across the 3D frames. We design a temporal variation-aware interpolation module and a temporal voxel-point refiner to capture the temporal variation in the 4D point cloud. The temporal variation-aware interpolation generates local features from the previous and current frames by capturing spatial coherence and temporal variation information. The temporal voxel-point refiner builds a temporal graph on the 3D point cloud sequences and captures the temporal variation with a graph convolution module. The temporal voxel-point refiner also transforms the coarse voxel-level predictions into fine point-level predictions. With our proposed modules, the new network TVSN achieves state-of-the-art performance on SemanticKITTI and SemantiPOSS. Specifically, our method achieves 52.5\% in mIoU (+5.5% against previous best approaches) on the multiple scan segmentation task on SemanticKITTI, and 63.0% on SemanticPOSS (+2.8% against previous best approaches).

Xingshu Chen, Sicheng Yu, Chong Cheng et al.

This paper investigates the problem of object detection with a focus on improving both the localization accuracy of bounding boxes and explicitly modeling prediction uncertainty. Conventional detectors rely on deterministic bounding box regression, ignoring uncertainty in predictions and limiting model robustness. In this paper, we propose an uncertainty-aware enhancement framework for DETR-based object detectors. We model bounding boxes as multivariate Gaussian distributions and incorporate the Gromov-Wasserstein distance into the loss function to better align the predicted and ground-truth distributions. Building on this, we derive a Bayes Risk formulation to filter high-risk information and improve detection reliability. We also propose a simple algorithm to quantify localization uncertainty via confidence intervals. Experiments on the COCO benchmark show that our method can be effectively integrated into existing DETR variants, enhancing their performance. We further extend our framework to leukocyte detection tasks, achieving state-of-the-art results on the LISC and WBCDD datasets. These results confirm the scalability of our framework across both general and domain-specific detection tasks. Code page: https://github.com/ParadiseforAndaChen/An-Uncertainty-aware-DETR-Enhancement-Framework-for-Object-Detection.

Hao Wang, Jinzhe Jiang, Xin Zhang et al.

As Large Language Models make a breakthrough in natural language processing tasks (NLP), multimodal technique becomes extremely popular. However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs of a model can be dramatically changed by a perturbation to the input. While several defense techniques have been proposed both in computer vision and NLP models, the multimodal robustness of models have not been fully explored. In this paper, we study the adversarial robustness provided by modifying loss function of pre-trained multimodal models, by restricting top K softmax outputs. Based on the evaluation and scoring, our experiments show that after a fine-tuning, adversarial robustness of pre-trained models can be significantly improved, against popular attacks. Further research should be studying, such as output diversity, generalization and the robustness-performance trade-off of this kind of loss functions. Our code will be available after this paper is accepted

Chen Long, Wenxiao Zhang, Ruihui Li et al.

Point cloud upsampling is to densify a sparse point set acquired from 3D sensors, providing a denser representation for the underlying surface. Existing methods divide the input points into small patches and upsample each patch separately, however, ignoring the global spatial consistency between patches. In this paper, we present a novel method PC$^2$-PU, which explores patch-to-patch and point-to-point correlations for more effective and robust point cloud upsampling. Specifically, our network has two appealing designs: (i) We take adjacent patches as supplementary inputs to compensate the loss structure information within a single patch and introduce a Patch Correlation Module to capture the difference and similarity between patches. (ii) After augmenting each patch's geometry, we further introduce a Point Correlation Module to reveal the relationship of points inside each patch to maintain the local spatial consistency. Extensive experiments on both synthetic and real scanned datasets demonstrate that our method surpasses previous upsampling methods, particularly with the noisy inputs. The code and data are at \url{https://github.com/chenlongwhu/PC2-PU.git}.

Jian Shu, Nanjie Yao, Gangjian Zhang et al.

3D human avatar animation aims at transforming a human avatar from an arbitrary initial pose to a specified target pose using deformation algorithms. Existing approaches typically divide this task into two stages: canonical template construction and target pose deformation. However, current template construction methods demand extensive skeletal rigging and often produce artifacts for specific poses. Moreover, target pose deformation suffers from structural distortions caused by Linear Blend Skinning (LBS), which significantly undermines animation realism. To address these problems, we propose a unified learning-based framework to address both challenges in two phases. For the former phase, to overcome the inefficiencies and artifacts during template construction, we leverage a U-Net architecture that decouples texture and pose information in a feed-forward process, enabling fast generation of a human template. For the latter phase, we propose a data-driven refinement technique that enhances structural integrity. Extensive experiments show that our model delivers consistent performance across diverse poses with an optimal balance between efficiency and quality,surpassing state-of-the-art (SOTA) methods.

Nanjie Yao, Gangjian Zhang, Wenhao Shen et al.

Monocular 3D clothed human reconstruction aims to create a complete 3D avatar from a single image. To tackle the human geometry lacking in one RGB image, current methods typically resort to a preceding model for an explicit geometric representation. For the reconstruction itself, focus is on modeling both it and the input image. This routine is constrained by the preceding model, and overlooks the integrity of the reconstruction task. To address this, this paper introduces a novel paradigm that treats human reconstruction as a holistic process, utilizing an end-to-end network for direct prediction from 2D image to 3D avatar, eliminating any explicit intermediate geometry display. Based on this, we further propose a novel reconstruction framework consisting of two core components: the Anatomy Shaping Extraction module, which captures implicit shape features taking into account the specialty of human anatomy, and the Twins Negotiating Reconstruction U-Net, which enhances reconstruction through feature interaction between two U-Nets of different modalities. Moreover, we propose a Comic Data Augmentation strategy and construct 15k+ 3D human scans to bolster model performance in more complex case input. Extensive experiments on two test sets and many in-the-wild cases show the superiority of our method over SOTA methods. Our demos can be found in : https://e2e3dgsrecon.github.io/e2e3dgsrecon/.

Hongbin Lin, Yifan Jiang, Juangui Xu et al.

3D point cloud segmentation aims to assign semantic labels to individual points in a scene for fine-grained spatial understanding. Existing methods typically adopt data augmentation to alleviate the burden of large-scale annotation. However, most augmentation strategies only focus on local transformations or semantic recomposition, lacking the consideration of global structural dependencies within scenes. To address this limitation, we propose a graph-guided data augmentation framework with dual-level constraints for realistic 3D scene synthesis. Our method learns object relationship statistics from real-world data to construct guiding graphs for scene generation. Local-level constraints enforce geometric plausibility and semantic consistency between objects, while global-level constraints maintain the topological structure of the scene by aligning the generated layout with the guiding graph. Extensive experiments on indoor and outdoor datasets demonstrate that our framework generates diverse and high-quality augmented scenes, leading to consistent improvements in point cloud segmentation performance across various models.

Jingtao Cao, Zheng Zhang, Hongru Wang et al.

Memes, which rapidly disseminate personal opinions and positions across the internet, also pose significant challenges in propagating social bias and prejudice. This study presents a novel approach to detecting harmful memes, particularly within the multicultural and multilingual context of Singapore. Our methodology integrates image captioning, Optical Character Recognition (OCR), and Large Language Model (LLM) analysis to comprehensively understand and classify harmful memes. Utilizing the BLIP model for image captioning, PP-OCR and TrOCR for text recognition across multiple languages, and the Qwen LLM for nuanced language understanding, our system is capable of identifying harmful content in memes created in English, Chinese, Malay, and Tamil. To enhance the system's performance, we fine-tuned our approach by leveraging additional data labeled using GPT-4V, aiming to distill the understanding capability of GPT-4V for harmful memes to our system. Our framework achieves top-1 at the public leaderboard of the Online Safety Prize Challenge hosted by AI Singapore, with the AUROC as 0.7749 and accuracy as 0.7087, significantly ahead of the other teams. Notably, our approach outperforms previous benchmarks, with FLAVA achieving an AUROC of 0.5695 and VisualBERT an AUROC of 0.5561.

Hao Wang, Guosheng Lin, Steven C. H. Hoi et al.

Food is significant to human daily life. In this paper, we are interested in learning structural representations for lengthy recipes, that can benefit the recipe generation and food cross-modal retrieval tasks. Different from the common vision-language data, here the food images contain mixed ingredients and target recipes are lengthy paragraphs, where we do not have annotations on structure information. To address the above limitations, we propose a novel method to unsupervisedly learn the sentence-level tree structures for the cooking recipes. Our approach brings together several novel ideas in a systematic framework: (1) exploiting an unsupervised learning approach to obtain the sentence-level tree structure labels before training; (2) generating trees of target recipes from images with the supervision of tree structure labels learned from (1); and (3) integrating the learned tree structures into the recipe generation and food cross-modal retrieval procedure. Our proposed model can produce good-quality sentence-level tree structures and coherent recipes. We achieve the state-of-the-art recipe generation and food cross-modal retrieval performance on the benchmark Recipe1M dataset.

Xingjian He, Weining Wang, Zhiyong Xu et al.

Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction. In this paper, we propose a Spatial-Temporal Semantic Consistency method to capture class-exclusive context information. Specifically, we design a spatial-temporal consistency loss to constrain the semantic consistency in spatial and temporal dimensions. In addition, we adopt an pseudo-labeling strategy to enrich the training dataset. We obtain the scores of 59.84% and 58.85% mIoU on development (test part 1) and testing set of VSPW, respectively. And our method wins the 1st place on VSPW challenge at ICCV2021.

Hao Wang, Guosheng Lin, Steven C. H. Hoi et al.

Video captioning targets interpreting the complex visual contents as text descriptions, which requires the model to fully understand video scenes including objects and their interactions. Prevailing methods adopt off-the-shelf object detection networks to give object proposals and use the attention mechanism to model the relations between objects. They often miss some undefined semantic concepts of the pretrained model and fail to identify exact predicate relationships between objects. In this paper, we investigate an open research task of generating text descriptions for the given videos, and propose Cross-Modal Graph (CMG) with meta concepts for video captioning. Specifically, to cover the useful semantic concepts in video captions, we weakly learn the corresponding visual regions for text descriptions, where the associated visual regions and textual words are named cross-modal meta concepts. We further build meta concept graphs dynamically with the learned cross-modal meta concepts. We also construct holistic video-level and local frame-level video graphs with the predicted predicates to model video sequence structures. We validate the efficacy of our proposed techniques with extensive experiments and achieve state-of-the-art results on two public datasets.

Hao Wang, Guosheng Lin, Steven C. H. Hoi et al.

Recipe generation from food images and ingredients is a challenging task, which requires the interpretation of the information from another modality. Different from the image captioning task, where the captions usually have one sentence, cooking instructions contain multiple sentences and have obvious structures. To help the model capture the recipe structure and avoid missing some cooking details, we propose a novel framework: Decomposing Generation Networks (DGN) with structure prediction, to get more structured and complete recipe generation outputs. Specifically, we split each cooking instruction into several phases, and assign different sub-generators to each phase. Our approach includes two novel ideas: (i) learning the recipe structures with the global structure prediction component and (ii) producing recipe phases in the sub-generator output component based on the predicted structure. Extensive experiments on the challenging large-scale Recipe1M dataset validate the effectiveness of our proposed model, which improves the performance over the state-of-the-art results.

Doyen Sahoo, Wang Hao, Shu Ke et al.

An important aspect of health monitoring is effective logging of food consumption. This can help management of diet-related diseases like obesity, diabetes, and even cardiovascular diseases. Moreover, food logging can help fitness enthusiasts, and people who wanting to achieve a target weight. However, food-logging is cumbersome, and requires not only taking additional effort to note down the food item consumed regularly, but also sufficient knowledge of the food item consumed (which is difficult due to the availability of a wide variety of cuisines). With increasing reliance on smart devices, we exploit the convenience offered through the use of smart phones and propose a smart-food logging system: FoodAI, which offers state-of-the-art deep-learning based image recognition capabilities. FoodAI has been developed in Singapore and is particularly focused on food items commonly consumed in Singapore. FoodAI models were trained on a corpus of 400,000 food images from 756 different classes. In this paper we present extensive analysis and insights into the development of this system. FoodAI has been deployed as an API service and is one of the components powering Healthy 365, a mobile app developed by Singapore's Heath Promotion Board. We have over 100 registered organizations (universities, companies, start-ups) subscribing to this service and actively receive several API requests a day. FoodAI has made food logging convenient, aiding smart consumption and a healthy lifestyle.

Xinxun Xu, Hao Wang, Leida Li et al.

Zero-shot sketch-based image retrieval (ZS-SBIR) is a specific cross-modal retrieval task for retrieving natural images with free-hand sketches under zero-shot scenario. Previous works mostly focus on modeling the correspondence between images and sketches or synthesizing image features with sketch features. However, both of them ignore the large intra-class variance of sketches, thus resulting in unsatisfactory retrieval performance. In this paper, we propose a novel end-to-end semantic adversarial approach for ZS-SBIR. Specifically, we devise a semantic adversarial module to maximize the consistency between learned semantic features and category-level word vectors. Moreover, to preserve the discriminability of synthesized features within each training category, a triplet loss is employed for the generative module. Additionally, the proposed model is trained in an end-to-end strategy to exploit better semantic features suitable for ZS-SBIR. Extensive experiments conducted on two large-scale popular datasets demonstrate that our proposed approach remarkably outperforms state-of-the-art approaches by more than 12\% on Sketchy dataset and about 3\% on TU-Berlin dataset in the retrieval.

Hao Wang, Doyen Sahoo, Chenghao Liu et al.

Food computing is playing an increasingly important role in human daily life, and has found tremendous applications in guiding human behavior towards smart food consumption and healthy lifestyle. An important task under the food-computing umbrella is retrieval, which is particularly helpful for health related applications, where we are interested in retrieving important information about food (e.g., ingredients, nutrition, etc.). In this paper, we investigate an open research task of cross-modal retrieval between cooking recipes and food images, and propose a novel framework Adversarial Cross-Modal Embedding (ACME) to resolve the cross-modal retrieval task in food domains. Specifically, the goal is to learn a common embedding feature space between the two modalities, in which our approach consists of several novel ideas: (i) learning by using a new triplet loss scheme together with an effective sampling strategy, (ii) imposing modality alignment using an adversarial learning strategy, and (iii) imposing cross-modal translation consistency such that the embedding of one modality is able to recover some important information of corresponding instances in the other modality. ACME achieves the state-of-the-art performance on the benchmark Recipe1M dataset, validating the efficacy of the proposed technique.

Hao Wang, Cheng Deng, Xinxu Xu et al.

Zero-shot sketch-based image retrieval (ZS-SBIR) is a task of cross-domain image retrieval from a natural image gallery with free-hand sketch under a zero-shot scenario. Previous works mostly focus on a generative approach that takes a highly abstract and sparse sketch as input and then synthesizes the corresponding natural image. However, the intrinsic visual sparsity and large intra-class variance of the sketch make the learning of the conditional decoder more difficult and hence achieve unsatisfactory retrieval performance. In this paper, we propose a novel stacked semantic-guided network to address the unique characteristics of sketches in ZS-SBIR. Specifically, we devise multi-layer feature fusion networks that incorporate different intermediate feature representation information in a deep neural network to alleviate the intrinsic sparsity of sketches. In order to improve visual knowledge transfer from seen to unseen classes, we elaborate a coarse-to-fine conditional decoder that generates coarse-grained category-specific corresponding features first (taking auxiliary semantic information as conditional input) and then generates fine-grained instance-specific corresponding features (taking sketch representation as conditional input). Furthermore, regression loss and classification loss are utilized to preserve the semantic and discriminative information of the synthesized features respectively. Extensive experiments on the large-scale Sketchy dataset and TU-Berlin dataset demonstrate that our proposed approach outperforms state-of-the-art methods by more than 20\% in retrieval performance.