arXiv subjects

Yao Tang

Publications and source records attributed to Yao Tang.

51 records · Page 3Linked to original sources

arXiv2024

FMPAF: How Do Fed Chairs Affect the Financial Market? A Fine-grained Monetary Policy Analysis Framework on Their Language

The effectiveness of central bank communication is a crucial aspect of monetary policy transmission. While recent research has examined the influence of policy communication by the chairs of the Federal Reserve on various financial variables, much of the literature relies on rule-based or dictionary-based methods in parsing the language of the chairs, leaving nuanced information about policy stance contained in nonverbal emotion out of the analysis. In the current study, we propose the Fine-Grained Monetary Policy Analysis Framework (FMPAF), a novel approach that integrates large language models (LLMs) with regression analysis to provide a comprehensive analysis of the impact of the press-conference communications of chairs of the Federal Reserve on financial markets. We conduct extensive comparisons of model performance under different levels of granularity, modalities, and communication scenarios. Based on our preferred specification, a one-unit increase in the sentiment score is associated with an increase of the price of S\&P 500 Exchange-Traded Fund by approximately 500 basis points, a 15-basis-point decrease in the policy interest rate, while not leading to a significant response in exchange rates.

cs.CL↗

arXiv2024

A Simple Baseline for Efficient Hand Mesh Reconstruction

3D hand pose estimation has found broad application in areas such as gesture recognition and human-machine interaction tasks. As performance improves, the complexity of the systems also increases, which can limit the comparative analysis and practical implementation of these methods. In this paper, we propose a simple yet effective baseline that not only surpasses state-of-the-art (SOTA) methods but also demonstrates computational efficiency. To establish this baseline, we abstract existing work into two components: a token generator and a mesh regressor, and then examine their core structures. A core structure, in this context, is one that fulfills intrinsic functions, brings about significant improvements, and achieves excellent performance without unnecessary complexities. Our proposed approach is decoupled from any modifications to the backbone, making it adaptable to any modern models. Our method outperforms existing solutions, achieving state-of-the-art (SOTA) results across multiple datasets. On the FreiHAND dataset, our approach produced a PA-MPJPE of 5.7mm and a PA-MPVPE of 6.0mm. Similarly, on the Dexycb dataset, we observed a PA-MPJPE of 5.5mm and a PA-MPVPE of 5.0mm. As for performance speed, our method reached up to 33 frames per second (fps) when using HRNet and up to 70 fps when employing FastViT-MA36

cs.CV↗

arXiv2023

FAAC: Facial Animation Generation with Anchor Frame and Conditional Control for Superior Fidelity and Editability

Over recent years, diffusion models have facilitated significant advancements in video generation. Yet, the creation of face-related videos still confronts issues such as low facial fidelity, lack of frame consistency, limited editability and uncontrollable human poses. To address these challenges, we introduce a facial animation generation method that enhances both face identity fidelity and editing capabilities while ensuring frame consistency. This approach incorporates the concept of an anchor frame to counteract the degradation of generative ability in original text-to-image models when incorporating a motion module. We propose two strategies towards this objective: training-free and training-based anchor frame methods. Our method's efficacy has been validated on multiple representative DreamBooth and LoRA models, delivering substantial improvements over the original outcomes in terms of facial fidelity, text-to-image editability, and video motion. Moreover, we introduce conditional control using a 3D parametric face model to capture accurate facial movements and expressions. This solution augments the creative possibilities for facial animation generation through the integration of multiple control signals. For additional samples, please visit https://paper-faac.github.io/.

cs.CV↗

arXiv2023

Boosting Generalization with Adaptive Style Techniques for Fingerprint Liveness Detection

We introduce a high-performance fingerprint liveness feature extraction technique that secured first place in LivDet 2023 Fingerprint Representation Challenge. Additionally, we developed a practical fingerprint recognition system with 94.68% accuracy, earning second place in LivDet 2023 Liveness Detection in Action. By investigating various methods, particularly style transfer, we demonstrate improvements in accuracy and generalization when faced with limited training data. As a result, our approach achieved state-of-the-art performance in LivDet 2023 Challenges.

cs.CV↗

arXiv2023

1st Place Solution of Egocentric 3D Hand Pose Estimation Challenge 2023 Technical Report:A Concise Pipeline for Egocentric Hand Pose Reconstruction

This report introduce our work on Egocentric 3D Hand Pose Estimation workshop. Using AssemblyHands, this challenge focuses on egocentric 3D hand pose estimation from a single-view image. In the competition, we adopt ViT based backbones and a simple regressor for 3D keypoints prediction, which provides strong model baselines. We noticed that Hand-objects occlusions and self-occlusions lead to performance degradation, thus proposed a non-model method to merge multi-view results in the post-process stage. Moreover, We utilized test time augmentation and model ensemble to make further improvement. We also found that public dataset and rational preprocess are beneficial. Our method achieved 12.21mm MPJPE on test dataset, achieve the first place in Egocentric 3D Hand Pose Estimation challenge.

cs.CV↗

arXiv2023

Integrated Sensing, Computation, and Communication for UAV-assisted Federated Edge Learning

Federated edge learning (FEEL) enables privacy-preserving model training through periodic communication between edge devices and the server. Unmanned Aerial Vehicle (UAV)-mounted edge devices are particularly advantageous for FEEL due to their flexibility and mobility in efficient data collection. In UAV-assisted FEEL, sensing, computation, and communication are coupled and compete for limited onboard resources, and UAV deployment also affects sensing and communication performance. Therefore, the joint design of UAV deployment and resource allocation is crucial to achieving the optimal training performance. In this paper, we address the problem of joint UAV deployment design and resource allocation for FEEL via a concrete case study of human motion recognition based on wireless sensing. We first analyze the impact of UAV deployment on the sensing quality and identify a threshold value for the sensing elevation angle that guarantees a satisfactory quality of data samples. Due to the non-ideal sensing channels, we consider the probabilistic sensing model, where the successful sensing probability of each UAV is determined by its position. Then, we derive the upper bound of the FEEL training loss as a function of the sensing probability. Theoretical results suggest that the convergence rate can be improved if UAVs have a uniform successful sensing probability. Based on this analysis, we formulate a training time minimization problem by jointly optimizing UAV deployment, integrated sensing, computation, and communication (ISCC) resources under a desirable optimality gap constraint. To solve this challenging mixed-integer non-convex problem, we apply the alternating optimization technique, and propose the bandwidth, batch size, and position optimization (BBPO) scheme to optimize these three decision variables alternately.

cs.IT↗

arXiv2023

Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers

Although vision transformers (ViTs) have shown promising results in various computer vision tasks recently, their high computational cost limits their practical applications. Previous approaches that prune redundant tokens have demonstrated a good trade-off between performance and computation costs. Nevertheless, errors caused by pruning strategies can lead to significant information loss. Our quantitative experiments reveal that the impact of pruned tokens on performance should be noticeable. To address this issue, we propose a novel joint Token Pruning & Squeezing module (TPS) for compressing vision transformers with higher efficiency. Firstly, TPS adopts pruning to get the reserved and pruned subsets. Secondly, TPS squeezes the information of pruned tokens into partial reserved tokens via the unidirectional nearest-neighbor matching and similarity-based fusing steps. Compared to state-of-the-art methods, our approach outperforms them under all token pruning intensities. Especially while shrinking DeiT-tiny&small computational budgets to 35%, it improves the accuracy by 1%-6% compared with baselines on ImageNet classification. The proposed method can accelerate the throughput of DeiT-small beyond DeiT-tiny, while its accuracy surpasses DeiT-tiny by 4.78%. Experiments on various transformers demonstrate the effectiveness of our method, while analysis experiments prove our higher robustness to the errors of the token pruning policy. Code is available at https://github.com/megvii-research/TPS-CVPR2023.

cs.CV↗

arXiv2022

Hazy with a chance of star spots: constraining the atmosphere of the young planet, K2-33b

Although all-sky surveys have led to the discovery of dozens of young planets, little is known about their atmospheres. Here, we present multi-wavelength transit data for the super Neptune-sized exoplanet, K2-33b -- the youngest (~10 Myr) transiting exoplanet to-date. We combined photometric observations of K2-33 covering a total of 33 transits spanning >2 years, taken from K2, MEarth, Hubble, and Spitzer. The transit photometry spanned from the optical to the near-infrared (0.6-4.5$μ$m), enabling us to construct a transmission spectrum of the planet. We find that the optical transit depths are nearly a factor of two deeper than those from the near-infrared. This difference holds across multiple datasets taken over years, ruling out issues of data analysis and unconstrained systematics. Surface inhomogeneities on the young star can reproduce some of the difference, but required spot coverage fractions (>60%) are ruled out by the observed stellar spectrum(<20%). We find a better fit to the transmission spectrum using photochemical hazes, which were predicted to be strong in young, moderate-temperature, and large-radius planets like K2-33b. A tholin haze with CO as the dominant gaseous carbon carrier in the atmosphere can reasonably reproduce the data with small or no stellar surface inhomogeneities, consistent with the stellar spectrum. The HST data quality is insufficient for the detection of any molecular features. More observations would be required to fully characterize the hazes and spot properties and confirm the presence of CO suggested by current data.

astro-ph.EP↗

arXiv2022

SimpleDG: Simple Domain Generalization Baseline without Bells and Whistles

We present a simple domain generalization baseline, which wins second place in both the common context generalization track and the hybrid context generalization track respectively in NICO CHALLENGE 2022. We verify the founding in recent literature, domainbed, that ERM is a strong baseline compared to recent state-of-the-art domain generalization methods and propose SimpleDG which includes several simple yet effective designs that further boost generalization performance. Code is available at https://github.com/megvii-research/SimpleDG

cs.CV↗

arXiv2022

Efficient One Pass Self-distillation with Zipf's Label Smoothing

Self-distillation exploits non-uniform soft supervision from itself during training and improves performance without any runtime cost. However, the overhead during training is often overlooked, and yet reducing time and memory overhead during training is increasingly important in the giant models' era. This paper proposes an efficient self-distillation method named Zipf's Label Smoothing (Zipf's LS), which uses the on-the-fly prediction of a network to generate soft supervision that conforms to Zipf distribution without using any contrastive samples or auxiliary parameters. Our idea comes from an empirical observation that when the network is duly trained the output values of a network's final softmax layer, after sorting by the magnitude and averaged across samples, should follow a distribution reminiscent to Zipf's Law in the word frequency statistics of natural languages. By enforcing this property on the sample level and throughout the whole training period, we find that the prediction accuracy can be greatly improved. Using ResNet50 on the INAT21 fine-grained classification dataset, our technique achieves +3.61% accuracy gain compared to the vanilla baseline, and 0.88% more gain against the previous label smoothing or self-distillation strategies. The implementation is publicly available at https://github.com/megvii-research/zipfls.

cs.CV↗

arXiv2020

Efficient CNOT Synthesis for NISQ Devices

In the era of noisy intermediate-scale quantum (NISQ), executing quantum algorithms on actual quantum devices faces unique challenges. One such challenge is that quantum devices in this era have restricted connectivity: quantum gates are allowed to act only on specific pairs of physical qubits. For this reason, a quantum circuit needs to go through a compiling process called qubit routing before it can be executed on a quantum computer. In this study, we propose a CNOT synthesis method called the token reduction method to solve this problem. The token reduction method works for all quantum computers whose architecture is represented by connected graphs. A major difference between our method and the existing ones is that our method synthesizes a circuit to an output qubit mapping that might be different from the input qubit mapping. The final mapping for the synthesis is determined dynamically during the synthesis process. Results showed that our algorithm consistently outperforms the best publicly accessible algorithm for all of the tested quantum architectures.

quant-ph↗

arXiv2019

Trajectory Design for Multiple-UAV Assisted Wireless Networks

Unmanned aerial vehicles (UAVs) can enhance the performance of cellular networks, due to their high mobility and efficient deployment. In this paper, we present a first study on how the user mobility affects the UAVs' trajectories of a multiple-UAV assisted wireless communication system. Specifically, we consider the UAVs are deployed as aerial base stations to serve ground users who move between different regions. We maximize the throughput of ground users in the downlink communication by optimizing the UAVs' trajectories, while taking into account the impact of the user mobility, propulsion energy consumption, and UAVs' mutual interference. We formulate the problem as a route selection problem in an acyclic directed graph. Each vertex represents a task associated with a reward on the average user throughput in a region-time point, while each edge is associated with a cost on the energy propulsion consumption during flying and hovering. For the centralized trajectory design, we first propose the shortest path scheme that determines the optimal trajectory for the single UAV case. We also propose the centralized route selection (CRS) scheme to systematically compute the optimal trajectories for the more general multiple-UAV case. Due to the NP-hardness of the centralized problem, we consider the distributed trajectory design that each UAV selects its trajectory autonomously and propose the distributed route selection (DRS) scheme, which will converge to a pure strategy Nash equilibrium within a finite number of iterations.

cs.IT↗

arXiv2017

Latent fingerprint minutia extraction using fully convolutional network

Minutiae play a major role in fingerprint identification. Extracting reliable minutiae is difficult for latent fingerprints which are usually of poor quality. As the limitation of traditional handcrafted features, a fully convolutional network (FCN) is utilized to learn features directly from data to overcome complex background noises. Raw fingerprints are mapped to a correspondingly-sized minutia-score map with a fixed stride. And thus a large number of minutiae will be extracted through a given threshold. Then small regions centering at these minutia points are entered into a convolutional neural network (CNN) to reclassify these minutiae and calculate their orientations. The CNN shares convolutional layers with the fully convolutional network to speed up. 0.45 second is used on average to detect one fingerprint on a GPU. On the NIST SD27 database, we achieve 53\% recall rate and 53\% precise rate that outperform many other algorithms. Our trained model is also visualized to show that we have successfully extracted features preserving ridge information of a latent fingerprint.

cs.CV↗

arXiv2017

FingerNet: An Unified Deep Network for Fingerprint Minutiae Extraction

Minutiae extraction is of critical importance in automated fingerprint recognition. Previous works on rolled/slap fingerprints failed on latent fingerprints due to noisy ridge patterns and complex background noises. In this paper, we propose a new way to design deep convolutional network combining domain knowledge and the representation ability of deep learning. In terms of orientation estimation, segmentation, enhancement and minutiae extraction, several typical traditional methods performed well on rolled/slap fingerprints are transformed into convolutional manners and integrated as an unified plain network. We demonstrate that this pipeline is equivalent to a shallow network with fixed weights. The network is then expanded to enhance its representation ability and the weights are released to learn complex background variance from data, while preserving end-to-end differentiability. Experimental results on NIST SD27 latent database and FVC 2004 slap database demonstrate that the proposed algorithm outperforms the state-of-the-art minutiae extraction algorithms. Code is made publicly available at: https://github.com/felixTY/FingerNet.

cs.CV↗

arXiv2013

A Partial Decode-Forward Scheme For A Network with N relays

We study a discrete-memoryless relay network consisting of one source, one destination and N relays, and design a scheme based on partial decode-forward relaying. The source splits its message into one common and N+1 private parts, one intended for each relay. It encodes these message parts using Nth-order block Markov coding, in which each private message part is independently superimposed on the common parts of the current and N previous blocks. Using simultaneous sliding window decoding, each relay fully recovers the common message and its intended private message with the same block index, then forwards them to the following nodes in the next block. This scheme can be applied to any network topology. We derive its achievable rate in a compact form. The result reduces to a known decode-forward lower bound for an N-relay network and partial decode-forward lower bound for a two-level relay network. We then apply the scheme to a Gaussian two-level relay network and obtain its capacity lower bound considering power constraints at the transmitting nodes.

cs.IT↗