Category-level 6D pose estimation, aiming to predict the location and orientation of unseen object instances, is fundamental to many scenarios such as robotic manipulation and augmented reality, yet still remains unsolved. Precisely recovering instance 3D model in the canonical space and accurately matching it with the observation is an essential point when estimating 6D pose for unseen objects. In this paper, we achieve accurate category-level 6D pose estimation via cascaded relation and recurrent reconstruction networks. Specifically, a novel cascaded relation network is dedicated for advanced representation learning to explore the complex and informative relations among instance RGB image, instance point cloud and category shape prior. Furthermore, we design a recurrent reconstruction network for iterative residual refinement to progressively improve the reconstruction and correspondence estimations from coarse to fine. Finally, the instance 6D pose is obtained leveraging the estimated dense correspondences between the instance point cloud and the reconstructed 3D model in the canonical space. We have conducted extensive experiments on two well-acknowledged benchmarks of category-level 6D pose estimation, with significant performance improvement over existing approaches. On the representatively strict evaluation metrics of $3D_{75}$ and $5^{\circ}2 cm$, our method exceeds the latest state-of-the-art SPD by $4.9\%$ and $17.7\%$ on the CAMERA25 dataset, and by $2.7\%$ and $8.5\%$ on the REAL275 dataset. Codes are available at https://wangjiaze.cn/projects/6DPoseEstimation.html.
Person re-identification via 3D skeletons is an emerging topic with great potential in security-critical applications. Existing methods typically learn body and motion features from the body-joint trajectory, whereas they lack a systematic way to model body structure and underlying relations of body components beyond the scale of body joints. In this paper, we for the first time propose a Self-supervised Multi-scale Skeleton Graph Encoding (SM-SGE) framework that comprehensively models human body, component relations, and skeleton dynamics from unlabeled skeleton graphs of various scales to learn an effective skeleton representation for person Re-ID. Specifically, we first devise multi-scale skeleton graphs with coarse-to-fine human body partitions, which enables us to model body structure and skeleton dynamics at multiple levels. Second, to mine inherent correlations between body components in skeletal motion, we propose a multi-scale graph relation network to learn structural relations between adjacent body-component nodes and collaborative relations among nodes of different scales, so as to capture more discriminative skeleton graph features. Last, we propose a novel multi-scale skeleton reconstruction mechanism to enable our framework to encode skeleton dynamics and high-level semantics from unlabeled skeleton graphs, which encourages learning a discriminative skeleton representation for person Re-ID. Extensive experiments show that SM-SGE outperforms most state-of-the-art skeleton-based methods. We further demonstrate its effectiveness on 3D skeleton data estimated from large-scale RGB videos. Our codes are open at https://github.com/Kali-Hac/SM-SGE.
This technical report presents our solution for temporal action detection task in AcitivityNet Challenge 2021. The purpose of this task is to locate and identify actions of interest in long untrimmed videos. The crucial challenge of the task comes from that the temporal duration of action varies dramatically, and the target actions are typically embedded in a background of irrelevant activities. Our solution builds on BMN, and mainly contains three steps: 1) action classification and feature encoding by Slowfast, CSN and ViViT; 2) proposal generation. We improve BMN by embedding the proposed Proposal Relation Network (PRN), by which we can generate proposals of high quality; 3) action detection. We calculate the detection results by assigning the proposals with corresponding classification results. Finally, we ensemble the results under different settings and achieve 44.7% on the test set, which improves the champion result in ActivityNet 2020 by 1.9% in terms of average mAP.
Is analogical reasoning a task that must be learned to solve from scratch by applying deep learning models to massive numbers of reasoning problems? Or are analogies solved by computing similarities between structured representations of analogs? We address this question by comparing human performance on visual analogies created using images of familiar three-dimensional objects (cars and their subregions) with the performance of alternative computational models. Human reasoners achieved above-chance accuracy for all problem types, but made more errors in several conditions (e.g., when relevant subregions were occluded). We compared human performance to that of two recent deep learning models (Siamese Network and Relation Network) directly trained to solve these analogy problems, as well as to that of a compositional model that assesses relational similarity between part-based representations. The compositional model based on part representations, but not the deep learning models, generated qualitative performance similar to that of human reasoners.
Contract element extraction (CEE) is the novel task of automatically identifying and extracting legally relevant elements such as contract dates, payments, and legislation references from contracts. Automatic methods for this task view it as a sequence labeling problem and dramatically reduce human labor. However, as contract genres and element types may vary widely, a significant challenge for this sequence labeling task is how to transfer knowledge from one domain to another, i.e., cross-domain CEE. Cross-domain CEE differs from cross-domain named entity recognition (NER) in two important ways. First, contract elements are far more fine-grained than named entities, which hinders the transfer of extractors. Second, the extraction zones for cross-domain CEE are much larger than for cross-domain NER. As a result, the contexts of elements from different domains can be more diverse. We propose a framework, the Bi-directional Feedback cLause-Element relaTion network (Bi-FLEET), for the cross-domain CEE task that addresses the above challenges. Bi-FLEET has three main components: (1) a context encoder, (2) a clause-element relation encoder, and (3) an inference layer. To incorporate invariant knowledge about element and clause types, a clause-element graph is constructed across domains and a hierarchical graph neural network is adopted in the clause-element relation encoder. To reduce the influence of context variations, a multi-task framework with a bi-directional feedback scheme is designed in the inference layer, conducting both clause classification and element extraction. The experimental results over both cross-domain NER and CEE tasks show that Bi-FLEET significantly outperforms state-of-the-art baselines.
Accurate prediction of pedestrian crossing behaviors by autonomous vehicles can significantly improve traffic safety. Existing approaches often model pedestrian behaviors using trajectories or poses but do not offer a deeper semantic interpretation of a person's actions or how actions influence a pedestrian's intention to cross in the future. In this work, we follow the neuroscience and psychological literature to define pedestrian crossing behavior as a combination of an unobserved inner will (a probabilistic representation of binary intent of crossing vs. not crossing) and a set of multi-class actions (e.g., walking, standing, etc.). Intent generates actions, and the future actions in turn reflect the intent. We present a novel multi-task network that predicts future pedestrian actions and uses predicted future action as a prior to detect the present intent and action of the pedestrian. We also designed an attention relation network to incorporate external environmental contexts thus further improve intent and action detection performance. We evaluated our approach on two naturalistic driving datasets, PIE and JAAD, and extensive experiments show significantly improved and more explainable results for both intent detection and action prediction over state-of-the-art approaches. Our code is available at: https://github.com/umautobots/pedestrian_intent_action_detection.
Instance level detection and segmentation of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images. Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN. The SAR-Net consists of three relation modules: 1. the anatomical structure relation module encoding spatial relations between diseases and anatomical parts. 2. the contextual relation module aggregating clues based on query-key pair of disease RoI and lung fields. 3. the disease relation module propagating co-occurrence and causal relations into disease proposals. Towards making a practical system, we also provide ChestX-Det, a chest X-Ray dataset with instance-level annotations (boxes and masks). ChestX-Det is a subset of the public dataset NIH ChestX-ray14. It contains ~3500 images of 13 common disease categories labeled by three board-certified radiologists. We evaluate our SAR-Net on it and another dataset DR-Private. Experimental results show that it can enhance the strong baseline of Mask R-CNN with significant improvements. The ChestX-Det is released at https://github.com/Deepwise-AILab/ChestX-Det-Dataset.
Point cloud semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose "One Thing One Click," meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. Also, we adopt a relation network to generate per-category prototype and explicitly model the similarity among graph nodes to generate pseudo labels to guide the iterative training. Experimental results on both ScanNet-v2 and S3DIS show that our self-training approach, with extremely-sparse annotations, outperforms all existing weakly supervised methods for 3D semantic segmentation by a large margin, and our results are also comparable to those of the fully supervised counterparts.
Despite the great success of Siamese-based trackers, their performance under complicated scenarios is still not satisfying, especially when there are distractors. To this end, we propose a novel Siamese relation network, which introduces two efficient modules, i.e. Relation Detector (RD) and Refinement Module (RM). RD performs in a meta-learning way to obtain a learning ability to filter the distractors from the background while RM aims to effectively integrate the proposed RD into the Siamese framework to generate accurate tracking result. Moreover, to further improve the discriminability and robustness of the tracker, we introduce a contrastive training strategy that attempts not only to learn matching the same target but also to learn how to distinguish the different objects. Therefore, our tracker can achieve accurate tracking results when facing background clutters, fast motion, and occlusion. Experimental results on five popular benchmarks, including VOT2018, VOT2019, OTB100, LaSOT, and UAV123, show that the proposed method is effective and can achieve state-of-the-art results. The code will be available at https://github.com/hqucv/siamrn
Automatic surgical workflow recognition is a key component for developing context-aware computer-assisted systems in the operating theatre. Previous works either jointly modeled the spatial features with short fixed-range temporal information, or separately learned visual and long temporal cues. In this paper, we propose a novel end-to-end temporal memory relation network (TMRNet) for relating long-range and multi-scale temporal patterns to augment the present features. We establish a long-range memory bank to serve as a memory cell storing the rich supportive information. Through our designed temporal variation layer, the supportive cues are further enhanced by multi-scale temporal-only convolutions. To effectively incorporate the two types of cues without disturbing the joint learning of spatio-temporal features, we introduce a non-local bank operator to attentively relate the past to the present. In this regard, our TMRNet enables the current feature to view the long-range temporal dependency, as well as tolerate complex temporal extents. We have extensively validated our approach on two benchmark surgical video datasets, M2CAI challenge dataset and Cholec80 dataset. Experimental results demonstrate the outstanding performance of our method, consistently exceeding the state-of-the-art methods by a large margin (e.g., 67.0% v.s. 78.9% Jaccard on Cholec80 dataset).
Weakly supervised instance segmentation reduces the cost of annotations required to train models. However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of objects and (b) missing object predictions. We show that these issues can be better addressed by training with weakly labeled videos instead of images. In videos, motion and temporal consistency of predictions across frames provide complementary signals which can help segmentation. We are the first to explore the use of these video signals to tackle weakly supervised instance segmentation. We propose two ways to leverage this information in our model. First, we adapt inter-pixel relation network (IRN) to effectively incorporate motion information during training. Second, we introduce a new MaskConsist module, which addresses the problem of missing object instances by transferring stable predictions between neighboring frames during training. We demonstrate that both approaches together improve the instance segmentation metric $AP_{50}$ on video frames of two datasets: Youtube-VIS and Cityscapes by $5\%$ and $3\%$ respectively.
Polyp segmentation is of great importance in the early diagnosis and treatment of colorectal cancer. Since polyps vary in their shape, size, color, and texture, accurate polyp segmentation is very challenging. One promising way to mitigate the diversity of polyps is to model the contextual relation for each pixel such as using attention mechanism. However, previous methods only focus on learning the dependencies between the position within an individual image and ignore the contextual relation across different images. In this paper, we propose Duplex Contextual Relation Network (DCRNet) to capture both within-image and cross-image contextual relations. Specifically, we first design Interior Contextual-Relation Module to estimate the similarity between each position and all the positions within the same image. Then Exterior Contextual-Relation Module is incorporated to estimate the similarity between each position and the positions across different images. Based on the above two types of similarity, the feature at one position can be further enhanced by the contextual region embedding within and across images. To store the characteristic region embedding from all the images, a memory bank is designed and operates as a queue. Therefore, the proposed method can relate similar features even though they come from different images. We evaluate the proposed method on the EndoScene, Kvasir-SEG and the recently released large-scale PICCOLO dataset. Experimental results show that the proposed DCRNet outperforms the state-of-the-art methods in terms of the widely-used evaluation metrics.
Question answering systems usually use keyword searches to retrieve potential passages related to a question, and then extract the answer from passages with the machine reading comprehension methods. However, many questions tend to be unanswerable in the real world. In this case, it is significant and challenging how the model determines when no answer is supported by the passage and abstains from answering. Most of the existing systems design a simple classifier to determine answerability implicitly without explicitly modeling mutual interaction and relation between the question and passage, leading to the poor performance for determining the unanswerable questions. To tackle this problem, we propose a Multi-Step Co-Interactive Relation Network (MCR-Net) to explicitly model the mutual interaction and locate key clues from coarse to fine by introducing a co-interactive relation module. The co-interactive relation module contains a stack of interaction and fusion blocks to continuously integrate and fuse history-guided and current-query-guided clues in an explicit way. Experiments on the SQuAD 2.0 and DuReader datasets show that our model achieves a remarkable improvement, outperforming the BERT-style baselines in literature. Visualization analysis also verifies the importance of the mutual interaction between the question and passage.
Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training. To bridge the gap between the seen and unseen classes, most GZSL methods attempt to associate the visual features of seen classes with attributes or to generate unseen samples directly. Nevertheless, the visual features used in the prior approaches do not necessarily encode semantically related information that the shared attributes refer to, which degrades the model generalization to unseen classes. To address this issue, in this paper, we propose a novel semantics disentangling framework for the generalized zero-shot learning task (SDGZSL), where the visual features of unseen classes are firstly estimated by a conditional VAE and then factorized into semantic-consistent and semantic-unrelated latent vectors. In particular, a total correlation penalty is applied to guarantee the independence between the two factorized representations, and the semantic consistency of which is measured by the derived relation network. Extensive experiments conducted on four GZSL benchmark datasets have evidenced that the semantic-consistent features disentangled by the proposed SDGZSL are more generalizable in tasks of canonical and generalized zero-shot learning. Our source code is available at https://github.com/uqzhichen/SDGZSL.
Semantic parsing has long been a fundamental problem in natural language processing. Recently, cross-domain context-dependent semantic parsing has become a new focus of research. Central to the problem is the challenge of leveraging contextual information of both natural language utterance and database schemas in the interaction history. In this paper, we present a dynamic graph framework that is capable of effectively modelling contextual utterances, tokens, database schemas, and their complicated interaction as the conversation proceeds. The framework employs a dynamic memory decay mechanism that incorporates inductive bias to integrate enriched contextual relation representation, which is further enhanced with a powerful reranking model. At the time of writing, we demonstrate that the proposed framework outperforms all existing models by large margins, achieving new state-of-the-art performance on two large-scale benchmarks, the SParC and CoSQL datasets. Specifically, the model attains a 55.8% question-match and 30.8% interaction-match accuracy on SParC, and a 46.8% question-match and 17.0% interaction-match accuracy on CoSQL.
Geospatial object segmentation, as a particular semantic segmentation task, always faces with larger-scale variation, larger intra-class variance of background, and foreground-background imbalance in the high spatial resolution (HSR) remote sensing imagery. However, general semantic segmentation methods mainly focus on scale variation in the natural scene, with inadequate consideration of the other two problems that usually happen in the large area earth observation scene. In this paper, we argue that the problems lie on the lack of foreground modeling and propose a foreground-aware relation network (FarSeg) from the perspectives of relation-based and optimization-based foreground modeling, to alleviate the above two problems. From perspective of relation, FarSeg enhances the discrimination of foreground features via foreground-correlated contexts associated by learning foreground-scene relation. Meanwhile, from perspective of optimization, a foreground-aware optimization is proposed to focus on foreground examples and hard examples of background during training for a balanced optimization. The experimental results obtained using a large scale dataset suggest that the proposed method is superior to the state-of-the-art general semantic segmentation methods and achieves a better trade-off between speed and accuracy. Code has been made available at: \url{https://github.com/Z-Zheng/FarSeg}.
Video QA challenges modelers in multiple fronts. Modeling video necessitates building not only spatio-temporal models for the dynamic visual channel but also multimodal structures for associated information channels such as subtitles or audio. Video QA adds at least two more layers of complexity - selecting relevant content for each channel in the context of the linguistic query, and composing spatio-temporal concepts and relations in response to the query. To address these requirements, we start with two insights: (a) content selection and relation construction can be jointly encapsulated into a conditional computational structure, and (b) video-length structures can be composed hierarchically. For (a) this paper introduces a general-reusable neural unit dubbed Conditional Relation Network (CRN) taking as input a set of tensorial objects and translating into a new set of objects that encode relations of the inputs. The generic design of CRN helps ease the common complex model building process of Video QA by simple block stacking with flexibility in accommodating input modalities and conditioning features across both different domains. As a result, we realize insight (b) by introducing Hierarchical Conditional Relation Networks (HCRN) for Video QA. The HCRN primarily aims at exploiting intrinsic properties of the visual content of a video and its accompanying channels in terms of compositionality, hierarchy, and near and far-term relation. HCRN is then applied for Video QA in two forms, short-form where answers are reasoned solely from the visual content, and long-form where associated information, such as subtitles, presented. Our rigorous evaluations show consistent improvements over SOTAs on well-studied benchmarks including large-scale real-world datasets such as TGIF-QA and TVQA, demonstrating the strong capabilities of our CRN unit and the HCRN for complex domains such as Video QA.
Social media plays a significant role in disaster management by providing valuable data about affected people, donations and help requests. Recent studies highlight the need to filter information on social media into fine-grained content labels. However, identifying useful information from massive amounts of social media posts during a crisis is a challenging task. In this paper, we propose I-AID, a multimodel approach to automatically categorize tweets into multi-label information types and filter critical information from the enormous volume of social media data. I-AID incorporates three main components: i) a BERT-based encoder to capture the semantics of a tweet and represent as a low-dimensional vector, ii) a graph attention network (GAT) to apprehend correlations between tweets' words/entities and the corresponding information types, and iii) a Relation Network as a learnable distance metric to compute the similarity between tweets and their corresponding information types in a supervised way. We conducted several experiments on two real publicly-available datasets. Our results indicate that I-AID outperforms state-of-the-art approaches in terms of weighted average F1 score by +6% and +4% on the TREC-IS dataset and COVID-19 Tweets, respectively.
Meta-learning approaches have shown great success in vision and language domains. However, few studies discuss the practice of meta-learning for large-scale industrial applications. Although e-commerce companies have spent many efforts on learning representations to provide a better user experience, we argue that such efforts cannot be stopped at this step. In addition to learning a strong profile, the challenging question about how to effectively transfer the learned representation is raised simultaneously. This paper introduces the contributions that we made to address these challenges from three aspects. 1) Meta-learning model: In the context of representation learning with e-commerce user behavior data, we propose a meta-learning framework called the Meta-Profile Network, which extends the ideas of matching network and relation network for knowledge transfer and fast adaptation; 2) Encoding strategy: To keep high fidelity of large-scale long-term sequential behavior data, we propose a time-heatmap encoding strategy that allows the model to encode data effectively; 3) Deep network architecture: A multi-modal model combined with multi-task learning architecture is utilized to address the cross-domain knowledge learning and insufficient label problems. Moreover, we argue that an industrial model should not only have good performance in terms of accuracy, but also have better robustness and uncertainty performance under extreme conditions. We evaluate the performance of our model with extensive control experiments in various extreme scenarios, i.e. out-of-distribution detection, data insufficiency and class imbalance scenarios. The Meta-Profile Network shows significant improvement in the model performance when compared to baseline models.
Spatio-temporal video grounding aims to retrieve the spatio-temporal tube of a queried object according to the given sentence. Currently, most existing grounding methods are restricted to well-aligned segment-sentence pairs. In this paper, we explore spatio-temporal video grounding on unaligned data and multi-form sentences. This challenging task requires to capture critical object relations to identify the queried target. However, existing approaches cannot distinguish notable objects and remain in ineffective relation modeling between unnecessary objects. Thus, we propose a novel object-aware multi-branch relation network for object-aware relation discovery. Concretely, we first devise multiple branches to develop object-aware region modeling, where each branch focuses on a crucial object mentioned in the sentence. We then propose multi-branch relation reasoning to capture critical object relationships between the main branch and auxiliary branches. Moreover, we apply a diversity loss to make each branch only pay attention to its corresponding object and boost multi-branch learning. The extensive experiments show the effectiveness of our proposed method.