arXiv subjects

Xiangyu Wu

Publications and source records attributed to Xiangyu Wu.

At least 73 records · Page 4Linked to original sources

arXiv2023

Solution for SMART-101 Challenge of ICCV Multi-modal Algorithmic Reasoning Task 2023

In this paper, we present our solution to a Multi-modal Algorithmic Reasoning Task: SMART-101 Challenge. Different from the traditional visual question-answering datasets, this challenge evaluates the abstraction, deduction, and generalization abilities of neural networks in solving visuolinguistic puzzles designed specifically for children in the 6-8 age group. We employed a divide-and-conquer approach. At the data level, inspired by the challenge paper, we categorized the whole questions into eight types and utilized the llama-2-chat model to directly generate the type for each question in a zero-shot manner. Additionally, we trained a yolov7 model on the icon45 dataset for object detection and combined it with the OCR method to recognize and locate objects and text within the images. At the model level, we utilized the BLIP-2 model and added eight adapters to the image encoder VIT-G to adaptively extract visual features for different question types. We fed the pre-constructed question templates as input and generated answers using the flan-t5-xxl decoder. Under the puzzle splits configuration, we achieved an accuracy score of 26.5 on the validation set and 24.30 on the private test set.

cs.CV↗

arXiv2023

NICE: CVPR 2023 Challenge on Zero-shot Image Captioning

In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed to challenge the computer vision community to develop robust image captioning models that advance the state-of-the-art both in terms of accuracy and fairness. Through the challenge, the image captioning models were tested using a new evaluation dataset that includes a large variety of visual concepts from many domains. There was no specific training data provided for the challenge, and therefore the challenge entries were required to adapt to new types of image descriptions that had not been seen during training. This report includes information on the newly proposed NICE dataset, evaluation methods, challenge results, and technical details of top-ranking entries. We expect that the outcomes of the challenge will contribute to the improvement of AI models on various vision-language tasks.

cs.CV↗

arXiv2023

CoVLR: Coordinating Cross-Modal Consistency and Intra-Modal Structure for Vision-Language Retrieval

Current vision-language retrieval aims to perform cross-modal instance search, in which the core idea is to learn the consistent visionlanguage representations. Although the performance of cross-modal retrieval has greatly improved with the development of deep models, we unfortunately find that traditional hard consistency may destroy the original relationships among single-modal instances, leading the performance degradation for single-modal retrieval. To address this challenge, in this paper, we experimentally observe that the vision-language divergence may cause the existence of strong and weak modalities, and the hard cross-modal consistency cannot guarantee that strong modal instances' relationships are not affected by weak modality, resulting in the strong modal instances' relationships perturbed despite learned consistent representations.To this end, we propose a novel and directly Coordinated VisionLanguage Retrieval method (dubbed CoVLR), which aims to study and alleviate the desynchrony problem between the cross-modal alignment and single-modal cluster-preserving tasks. CoVLR addresses this challenge by developing an effective meta-optimization based strategy, in which the cross-modal consistency objective and the intra-modal relation preserving objective are acted as the meta-train and meta-test tasks, thereby CoVLR encourages both tasks to be optimized in a coordinated way. Consequently, we can simultaneously insure cross-modal consistency and intra-modal structure. Experiments on different datasets validate CoVLR can improve single-modal retrieval accuracy whilst preserving crossmodal retrieval capacity compared with the baselines.

cs.CV↗

arXiv2023

Design and control of a collision-resilient aerial vehicle with an icosahedron tensegrity structure

We introduce collision-resilient aerial vehicles with icosahedron tensegrity structures, capable of surviving high-speed impacts and resuming operations post-collision. We present a model-based design approach, which guides the selection of the tensegrity components by predicting structural stresses through a dynamics simulation. Furthermore, we develop an autonomous re-orientation controller that facilitates post-collision flight resumption. The controller enables the vehicles to rotate from an arbitrary orientation on the ground for takeoff. With collision resilience and re-orientation ability, the tensegrity aerial vehicles can operate in cluttered environments without complex collision-avoidance strategies. These capabilities are validated by a test of an experimental vehicle operating autonomously in a previously-unknown forest environment.

cs.RO↗

arXiv2023

ContentCTR: Frame-level Live Streaming Click-Through Rate Prediction with Multimodal Transformer

In recent years, live streaming platforms have gained immense popularity as they allow users to broadcast their videos and interact in real-time with hosts and peers. Due to the dynamic changes of live content, accurate recommendation models are crucial for enhancing user experience. However, most previous works treat the live as a whole item and explore the Click-through-Rate (CTR) prediction framework on item-level, neglecting that the dynamic changes that occur even within the same live room. In this paper, we proposed a ContentCTR model that leverages multimodal transformer for frame-level CTR prediction. First, we present an end-to-end framework that can make full use of multimodal information, including visual frames, audio, and comments, to identify the most attractive live frames. Second, to prevent the model from collapsing into a mediocre solution, a novel pairwise loss function with first-order difference constraints is proposed to utilize the contrastive information existing in the highlight and non-highlight frames. Additionally, we design a temporal text-video alignment module based on Dynamic Time Warping to eliminate noise caused by the ambiguity and non-sequential alignment of visual and textual information. We conduct extensive experiments on both real-world scenarios and public datasets, and our ContentCTR model outperforms traditional recommendation models in capturing real-time content changes. Moreover, we deploy the proposed method on our company platform, and the results of online A/B testing further validate its practical significance.

cs.CV↗

arXiv2023

Learning a Single Near-hover Position Controller for Vastly Different Quadcopters

This paper proposes an adaptive near-hover position controller for quadcopters, which can be deployed to quadcopters of very different mass, size and motor constants, and also shows rapid adaptation to unknown disturbances during runtime. The core algorithmic idea is to learn a single policy that can adapt online at test time not only to the disturbances applied to the drone, but also to the robot dynamics and hardware in the same framework. We achieve this by training a neural network to estimate a latent representation of the robot and environment parameters, which is used to condition the behaviour of the controller, also represented as a neural network. We train both networks exclusively in simulation with the goal of flying the quadcopters to goal positions and avoiding crashes to the ground. We directly deploy the same controller trained in the simulation without any modifications on two quadcopters in the real world with differences in mass, size, motors, and propellers with mass differing by 4.5 times. In addition, we show rapid adaptation to sudden and large disturbances up to one-third of the mass of the quadcopters. We perform an extensive evaluation in both simulation and the physical world, where we outperform a state-of-the-art learning-based adaptive controller and a traditional PID controller specifically tuned to each platform individually. Video results can be found at https://youtu.be/U-c-LbTfvoA.

cs.RO↗

arXiv2023

A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset

Video understanding is an important task in short video business platforms and it has a wide application in video recommendation and classification. Most of the existing video understanding works only focus on the information that appeared within the video content, including the video frames, audio and text. However, introducing common sense knowledge from the external Knowledge Graph (KG) dataset is essential for video understanding when referring to the content which is less relevant to the video. Owing to the lack of video knowledge graph dataset, the work which integrates video understanding and KG is rare. In this paper, we propose a heterogeneous dataset that contains the multi-modal video entity and fruitful common sense relations. This dataset also provides multiple novel video inference tasks like the Video-Relation-Tag (VRT) and Video-Relation-Video (VRV) tasks. Furthermore, based on this dataset, we propose an end-to-end model that jointly optimizes the video understanding objective with knowledge graph embedding, which can not only better inject factual knowledge into video understanding but also generate effective multi-modal entity embedding for KG. Comprehensive experiments indicate that combining video understanding embedding with factual knowledge benefits the content-based video retrieval performance. Moreover, it also helps the model generate better knowledge graph embedding which outperforms traditional KGE-based methods on VRT and VRV tasks with at least 42.36% and 17.73% improvement in HITS@10.

cs.CV↗

arXiv2023

Generation-Guided Multi-Level Unified Network for Video Grounding

Video grounding aims to locate the timestamps best matching the query description within an untrimmed video. Prevalent methods can be divided into moment-level and clip-level frameworks. Moment-level approaches directly predict the probability of each transient moment to be the boundary in a global perspective, and they usually perform better in coarse grounding. On the other hand, clip-level ones aggregate the moments in different time windows into proposals and then deduce the most similar one, leading to its advantage in fine-grained grounding. In this paper, we propose a multi-level unified framework to enhance performance by leveraging the merits of both moment-level and clip-level methods. Moreover, a novel generation-guided paradigm in both levels is adopted. It introduces a multi-modal generator to produce the implicit boundary feature and clip feature, later regarded as queries to calculate the boundary scores by a discriminator. The generation-guided solution enhances video grounding from a two-unique-modals' match task to a cross-modal attention task, which steps out of the previous framework and obtains notable gains. The proposed Generation-guided Multi-level Unified network (GMU) surpasses previous methods and reaches State-Of-The-Art on various benchmarks with disparate features, e.g., Charades-STA, ActivityNet captions.

cs.CV↗

arXiv2023

Design, Modeling and Control of a Top-loading Fully-Actuated Cargo Transportation Multirotor

Existing multirotor-based cargo transportation does not maintain a constant cargo attitude due to underactuation; however, fragile payloads may require a consistent posture. The conventional method is also cumbersome when loading cargo, and the size of the cargo to be loaded is limited. To overcome these issues, we propose a new fully-actuated multirotor unmanned aerial vehicle platform capable of translational motion while maintaining a constant attitude. Our newly developed platform has a cubic exterior and can freely place cargo at any point on the flat top surface. However, the center-of-mass (CoM) position changes when cargo is loaded, leading to undesired attitudinal motion due to unwanted torque generation. To address this problem, we introduce a new model-free center-of-mass position estimation method inspired by the extremum-seeking control (ESC) technique. Experimental results are presented to validate the performance of the proposed estimation method, effectively estimating the CoM position and showing satisfactory constant-attitude flight performance.

cs.RO↗

arXiv2022

Perception-aware receding horizon trajectory planning for multicopters with visual-inertial odometry

Visual inertial odometry (VIO) is widely used for the state estimation of multicopters, but it may function poorly in environments with few visual features or in overly aggressive flights. In this work, we propose a perception-aware collision avoidance trajectory planner for multicopters, that may be used with any feature-based VIO algorithm. Our approach is able to fly the vehicle to a goal position at fast speed, avoiding obstacles in an unknown stationary environment while achieving good VIO state estimation accuracy. The proposed planner samples a group of minimum jerk trajectories and finds collision-free trajectories among them, which are then evaluated based on their speed to the goal and perception quality. Both the motion blur of features and their locations are considered for the perception quality. Our novel consideration of the motion blur of features enables automatic adaptation of the trajectory's aggressiveness under environments with different light levels. The best trajectory from the evaluation is tracked by the vehicle and is updated in a receding horizon manner when new images are received from the camera. Only generic assumptions about the VIO are made, so that the planner may be used with various existing systems. The proposed method can run in real-time on a small embedded computer on board. We validated the effectiveness of our proposed approach through experiments in both indoor and outdoor environments. Compared to a perception-agnostic planner, the proposed planner kept more features in the camera's view and made the flight less aggressive, making the VIO more accurate. It also reduced VIO failures, which occurred for the perception-agnostic planner but not for the proposed planner. The ability of the proposed planner to fly through dense obstacles was also validated. The experiment video can be found at https://youtu.be/qO3LZIrpwtQ.

cs.RO↗

arXiv2022

Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned

This article presents the CERBERUS robotic system-of-systems, which won the DARPA Subterranean Challenge Final Event in 2021. The Subterranean Challenge was organized by DARPA with the vision to facilitate the novel technologies necessary to reliably explore diverse underground environments despite the grueling challenges they present for robotic autonomy. Due to their geometric complexity, degraded perceptual conditions combined with lack of GPS support, austere navigation conditions, and denied communications, subterranean settings render autonomous operations particularly demanding. In response to this challenge, we developed the CERBERUS system which exploits the synergy of legged and flying robots, coupled with robust control especially for overcoming perilous terrain, multi-modal and multi-robot perception for localization and mapping in conditions of sensor degradation, and resilient autonomy through unified exploration path planning and local motion planning that reflects robot-specific limitations. Based on its ability to explore diverse underground environments and its high-level command and control by a single human supervisor, CERBERUS demonstrated efficient exploration, reliable detection of objects of interest, and accurate mapping. In this article, we report results from both the preliminary runs and the final Prize Round of the DARPA Subterranean Challenge, and discuss highlights and challenges faced, alongside lessons learned for the benefit of the community.

cs.RO↗

arXiv2022

Model-free online motion adaptation for energy efficient flights of multicopters

Limited flight distance and time is a common problem for multicopters. We propose a method for finding the optimal speed and sideslip angle of a multicopter flying a given path to achieve either the longest flight distance or time. Since flight speed and sideslip are often free variables in multicopter path planning, they can be changed without changing the mission. The proposed method is based on a novel multivariable extremum seeking controller with adaptive step size, which is inspired by recent work from the machine learning community on stochastic optimization. Our method (a) does not require a power consumption model of the vehicle, (b) is computationally efficient and runs on low-cost embedded computers in real-time, and (c) converges faster than the standard extremum seeking controller with constant step size. We prove the stability of this approach and validate it through outdoor experiments. The method is shown to converge with different payloads and in the presence of wind. Compared to flying at the maximum achievable speed in the experiments with a uniformly selected random sideslip angle, flying at the optimal range speed and sideslip on average increases the flight range by 14.3% without payload and 19.4% with a box payload. In addition, compared to hovering, flying at the optimal endurance speed and sideslip increases the flight time by 7.5% without payload and 14.4% with a box payload. A video can be found at https://youtu.be/aLds8LVfogk.

cs.RO↗

arXiv2022

CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge

Autonomous exploration of subterranean environments constitutes a major frontier for robotic systems as underground settings present key challenges that can render robot autonomy hard to achieve. This has motivated the DARPA Subterranean Challenge, where teams of robots search for objects of interest in various underground environments. In response, the CERBERUS system-of-systems is presented as a unified strategy towards subterranean exploration using legged and flying robots. As primary robots, ANYmal quadruped systems are deployed considering their endurance and potential to traverse challenging terrain. For aerial robots, both conventional and collision-tolerant multirotors are utilized to explore spaces too narrow or otherwise unreachable by ground systems. Anticipating degraded sensing conditions, a complementary multi-modal sensor fusion approach utilizing camera, LiDAR, and inertial data for resilient robot pose estimation is proposed. Individual robot pose estimates are refined by a centralized multi-robot map optimization approach to improve the reported location accuracy of detected objects of interest in the DARPA-defined coordinate frame. Furthermore, a unified exploration path planning policy is presented to facilitate the autonomous operation of both legged and aerial robots in complex underground networks. Finally, to enable communication between the robots and the base station, CERBERUS utilizes a ground rover with a high-gain antenna and an optical fiber connection to the base station, alongside breadcrumbing of wireless nodes by our legged robots. We report results from the CERBERUS system-of-systems deployment at the DARPA Subterranean Challenge Tunnel and Urban Circuits, along with the current limitations and the lessons learned for the benefit of the community.

cs.RO↗

arXiv2021

Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss

Employing large-scale pre-trained model CLIP to conduct video-text retrieval task (VTR) has become a new trend, which exceeds previous VTR methods. Though, due to the heterogeneity of structures and contents between video and text, previous CLIP-based models are prone to overfitting in the training phase, resulting in relatively poor retrieval performance. In this paper, we propose a multi-stream Corpus Alignment network with single gate Mixture-of-Experts (CAMoE) and a novel Dual Softmax Loss (DSL) to solve the two heterogeneity. The CAMoE employs Mixture-of-Experts (MoE) to extract multi-perspective video representations, including action, entity, scene, etc., then align them with the corresponding part of the text. In this stage, we conduct massive explorations towards the feature extraction module and feature alignment module. DSL is proposed to avoid the one-way optimum-match which occurs in previous contrastive methods. Introducing the intrinsic prior of each pair in a batch, DSL serves as a reviser to correct the similarity matrix and achieves the dual optimal match. DSL is easy to implement with only one-line code but improves significantly. The results show that the proposed CAMoE and DSL are of strong efficiency, and each of them is capable of achieving State-of-The-Art (SOTA) individually on various benchmarks such as MSR-VTT, MSVD, and LSMDC. Further, with both of them, the performance is advanced to a big extend, surpassing the previous SOTA methods for around 4.6\% R@1 in MSR-VTT.

cs.CV↗

arXiv2021

Real-time Geo-localization Using Satellite Imagery and Topography for Unmanned Aerial Vehicles

The capabilities of autonomous flight with unmanned aerial vehicles (UAVs) have significantly increased in recent times. However, basic problems such as fast and robust geo-localization in GPS-denied environments still remain unsolved. Existing research has primarily concentrated on improving the accuracy of localization at the cost of long and varying computation time in various situations, which often necessitates the use of powerful ground station machines. In order to make image-based geo-localization online and pragmatic for lightweight embedded systems on UAVs, we propose a framework that is reliable in changing scenes, flexible about computing resource allocation and adaptable to common camera placements. The framework is comprised of two stages: offline database preparation and online inference. At the first stage, color images and depth maps are rendered as seen from potential vehicle poses quantized over the satellite and topography maps of anticipated flying areas. A database is then populated with the global and local descriptors of the rendered images. At the second stage, for each captured real-world query image, top global matches are retrieved from the database and the vehicle pose is further refined via local descriptor matching. We present field experiments of image-based localization on two different UAV platforms to validate our results.

cs.RO↗

arXiv2021

MlTr: Multi-label Classification with Transformer

The task of multi-label image classification is to recognize all the object labels presented in an image. Though advancing for years, small objects, similar objects and objects with high conditional probability are still the main bottlenecks of previous convolutional neural network(CNN) based models, limited by convolutional kernels' representational capacity. Recent vision transformer networks utilize the self-attention mechanism to extract the feature of pixel granularity, which expresses richer local semantic information, while is insufficient for mining global spatial dependence. In this paper, we point out the three crucial problems that CNN-based methods encounter and explore the possibility of conducting specific transformer modules to settle them. We put forward a Multi-label Transformer architecture(MlTr) constructed with windows partitioning, in-window pixel attention, cross-window attention, particularly improving the performance of multi-label image classification tasks. The proposed MlTr shows state-of-the-art results on various prevalent multi-label datasets such as MS-COCO, Pascal-VOC, and NUS-WIDE with 88.5%, 95.8%, and 65.5% respectively. The code will be available soon at https://github.com/starmemda/MlTr/

cs.CV↗

arXiv2021

CAT: Cross Attention in Vision Transformer

Since Transformer has found widespread use in NLP, the potential of Transformer in CV has been realized and has inspired many new approaches. However, the computation required for replacing word tokens with image patches for Transformer after the tokenization of the image is vast(e.g., ViT), which bottlenecks model training and inference. In this paper, we propose a new attention mechanism in Transformer termed Cross Attention, which alternates attention inner the image patch instead of the whole image to capture local information and apply attention between image patches which are divided from single-channel feature maps capture global information. Both operations have less computation than standard self-attention in Transformer. By alternately applying attention inner patch and between patches, we implement cross attention to maintain the performance with lower computational cost and build a hierarchical network called Cross Attention Transformer(CAT) for other vision tasks. Our base model achieves state-of-the-arts on ImageNet-1K, and improves the performance of other methods on COCO and ADE20K, illustrating that our network has the potential to serve as general backbones. The code and models are available at \url{https://github.com/linhezheng19/CAT}.

cs.CV↗

arXiv2021

Autonomous Flight through Cluttered Outdoor Environments Using a Memoryless Planner

This paper introduces a collision avoidance system for navigating a multicopter in cluttered outdoor environments based on the recent memory-less motion planner, rectangular pyramid partitioning using integrated depth sensors (RAPPIDS). The RAPPIDS motion planner generates collision-free flight trajectories at high speed with low computational cost using only the latest depth image. In this work we extend it to improve the performance of the planner by taking the following issues into account. (a) Changes in the dynamic characteristics of the multicopter that occur during flight, such as changes in motor input/output characteristics due to battery voltage drop. (b) The noise of the flight sensor, which can cause unwanted control input components. (c) Planner utility function which may not be suitable for the cluttered environment. Therefore, in this paper we introduce solutions to each of the above problems and propose a system for the successful operation of the RAPPIDS planner in an outdoor cluttered flight environment. At the end of the paper, we validate the proposed method's effectiveness by presenting the flight experiment results in a forest environment. A video can be found at www.youtube.com/channel/UCK-gErmvZlBODN5gQpNcpsg

cs.RO↗