Search arXiv⌕ Search

arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 649 records · Page 36Linked to original sources
arXiv2023

Design of laser uniform illumination system based on aspheric lens and compound ellipsoidal cavity

In order to achieve uniform laser illumination with small aperture diameter and large field Angle,study laser active illumination system.An aspheric mirror combined with a composite ellipsoidal cavity is designed to achieve uniform illumination in this paper.Through an aspheric mirror,the fundamental mode of Gaussian beam is shaped into double Gaussian radiation and Flat-top radiation.The double Gaussian radiation rays are reflected again by the complex ellipsoidal cavity and decomposed into equal radiation flux,which is superimposed with the through Flat-top radiation rays to form a uniform distribution.The parameters of the complex ellipsoidal cavity are obtained by mapping equalization algorithm.After the superposition of the aspherical transmission Flat-top shaping and the composite ellipsoidal cavity secondary reflection shaping,the aperture is 29.7mm,whose aperture angle is 84.0 degrees,and the uniformity is 92.7% with 2m distance and 3.6m diameter.The optimization of uniformity is influenced by three factors:RMS,transmission and reflection power density ratio MT/R and transmission and reflection overlap degree.RMS and MT/R determine the design effect of the composite ellipsoidal cavity, which depends on the maximum reflection Angle and transmission Angle.MT/R is negatively correlated with the maximum reflection of Angle,and RMS is positively correlated with the transmission Angle.When the maximum reflection Angle is set to 32.0 degrees and the transmission Angle to 8.0 degrees,the minimum root-mean-square focusing radius is 108.6um,and the minimum effective transmission reflection power density ratio is 1.07.The degree overlap of transmission and reflection directly affects the uniformity of the target plane.The degree of transmission and reflection is adjusted by setting an adjustment factor.When the adjustment factor is 0.9,the uniformity of the target plane reaches the maximum.

physics.optics↗
arXiv2023

SN 2022oqm -- a Ca-rich explosion of a compact progenitor embedded in C/O circumstellar material

We present the discovery and analysis of SN\,2022oqm, a Type Ic supernova (SN) detected $<1$\,day after explosion. The SN rises to a blue and short-lived (2\,days) initial peak. Early-time spectral observations of SN\,2022oqm show a hot (40,000\,K) continuum with high-ionization C and O absorption features at velocities of 4000\,km\,s$^{-1}$, while its photospheric radius expands at 20,000\,\kms, indicating a pre-existing distribution of expanding C/O material. After $\sim2.5$\,days, both the spectrum and light curves evolve into those of a typical SN Ic, with line velocities of $\sim10,000$\,km\,s$^{-1}$, in agreement with the photospheric radius evolution. The optical light curves reach a second peak at $t\approx15$\,days. By $t=60$\,days, the spectrum of \oqm\ becomes nearly nebular, displaying strong \ion{Ca}{2} and [\ion{Ca}{2}] emission with no detectable [\ion{O}{1}], marking this event as Ca-rich. The early behavior can be explained by $10^{-3}$\,\msun\ of optically thin circumstellar material (CSM) surrounding either (1) a massive compact progenitor such as a Wolf-Rayet star, (2) a massive stripped progenitor with an extended envelope, or (3) a binary system with a white dwarf. We propose that the early-time light curve is powered by both interaction of the ejecta with the optically thin CSM and shock cooling (in the massive-star scenario). The observations can be explained by CSM that is optically thick to X-ray photons, is optically thick in the lines as seen in the spectra, and is optically thin to visible-light continuum photons that come either from downscattered X-rays or from the shock-heated ejecta. Calculations show that this scenario is self-consistent.

astro-ph.HE↗
arXiv2023

Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentation

Tracking any given object(s) spatially and temporally is a common purpose in Visual Object Tracking (VOT) and Video Object Segmentation (VOS). Joint tracking and segmentation have been attempted in some studies but they often lack full compatibility of both box and mask in initialization and prediction, and mainly focus on single-object scenarios. To address these limitations, this paper proposes a Multi-object Mask-box Integrated framework for unified Tracking and Segmentation, dubbed MITS. Firstly, the unified identification module is proposed to support both box and mask reference for initialization, where detailed object information is inferred from boxes or directly retained from masks. Additionally, a novel pinpoint box predictor is proposed for accurate multi-object box prediction, facilitating target-oriented representation learning. All target objects are processed simultaneously from encoding to propagation and decoding, as a unified pipeline for VOT and VOS. Experimental results show MITS achieves state-of-the-art performance on both VOT and VOS benchmarks. Notably, MITS surpasses the best prior VOT competitor by around 6% on the GOT-10k test set, and significantly improves the performance of box initialization on VOS benchmarks. The code is available at https://github.com/yoxu515/MITS.

cs.CV↗
arXiv2023

CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation

Audio-visual video segmentation~(AVVS) aims to generate pixel-level maps of sound-producing objects within image frames and ensure the maps faithfully adhere to the given audio, such as identifying and segmenting a singing person in a video. However, existing methods exhibit two limitations: 1) they address video temporal features and audio-visual interactive features separately, disregarding the inherent spatial-temporal dependence of combined audio and video, and 2) they inadequately introduce audio constraints and object-level information during the decoding stage, resulting in segmentation outcomes that fail to comply with audio directives. To tackle these issues, we propose a decoupled audio-video transformer that combines audio and video features from their respective temporal and spatial dimensions, capturing their combined dependence. To optimize memory consumption, we design a block, which, when stacked, enables capturing audio-visual fine-grained combinatorial-dependence in a memory-efficient manner. Additionally, we introduce audio-constrained queries during the decoding phase. These queries contain rich object-level information, ensuring the decoded mask adheres to the sounds. Experimental results confirm our approach's effectiveness, with our framework achieving a new SOTA performance on all three datasets using two backbones. The code is available at \url{https://github.com/aspirinone/CATR.github.io}

cs.CV↗
arXiv2023

RMP: A Random Mask Pretrain Framework for Motion Prediction

As the pretraining technique is growing in popularity, little work has been done on pretrained learning-based motion prediction methods in autonomous driving. In this paper, we propose a framework to formalize the pretraining task for trajectory prediction of traffic participants. Within our framework, inspired by the random masked model in natural language processing (NLP) and computer vision (CV), objects' positions at random timesteps are masked and then filled in by the learned neural network (NN). By changing the mask profile, our framework can easily switch among a range of motion-related tasks. We show that our proposed pretraining framework is able to deal with noisy inputs and improves the motion prediction accuracy and miss rate, especially for objects occluded over time by evaluating it on Argoverse and NuScenes datasets.

cs.RO↗
arXiv2023

InvestLM: A Large Language Model for Investment using Financial Domain Instruction Tuning

We present a new financial domain large language model, InvestLM, tuned on LLaMA-65B (Touvron et al., 2023), using a carefully curated instruction dataset related to financial investment. Inspired by less-is-more-for-alignment (Zhou et al., 2023), we manually curate a small yet diverse instruction dataset, covering a wide range of financial related topics, from Chartered Financial Analyst (CFA) exam questions to SEC filings to Stackexchange quantitative finance discussions. InvestLM shows strong capabilities in understanding financial text and provides helpful responses to investment related questions. Financial experts, including hedge fund managers and research analysts, rate InvestLM's response as comparable to those of state-of-the-art commercial models (GPT-3.5, GPT-4 and Claude-2). Zero-shot evaluation on a set of financial NLP benchmarks demonstrates strong generalizability. From a research perspective, this work suggests that a high-quality domain specific LLM can be tuned using a small set of carefully curated instructions on a well-trained foundation model, which is consistent with the Superficial Alignment Hypothesis (Zhou et al., 2023). From a practical perspective, this work develops a state-of-the-art financial domain LLM with superior capability in understanding financial texts and providing helpful investment advice, potentially enhancing the work efficiency of financial professionals. We release the model parameters to the research community.

q-fin.GN↗
arXiv2023

AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion

Large-scale pre-trained vision-language models allow for the zero-shot text-based generation of 3D avatars. The previous state-of-the-art method utilized CLIP to supervise neural implicit models that reconstructed a human body mesh. However, this approach has two limitations. Firstly, the lack of avatar-specific models can cause facial distortion and unrealistic clothing in the generated avatars. Secondly, CLIP only provides optimization direction for the overall appearance, resulting in less impressive results. To address these limitations, we propose AvatarFusion, the first framework to use a latent diffusion model to provide pixel-level guidance for generating human-realistic avatars while simultaneously segmenting clothing from the avatar's body. AvatarFusion includes the first clothing-decoupled neural implicit avatar model that employs a novel Dual Volume Rendering strategy to render the decoupled skin and clothing sub-models in one space. We also introduce a novel optimization method, called Pixel-Semantics Difference-Sampling (PS-DS), which semantically separates the generation of body and clothes, and generates a variety of clothing styles. Moreover, we establish the first benchmark for zero-shot text-to-avatar generation. Our experimental results demonstrate that our framework outperforms previous approaches, with significant improvements observed in all metrics. Additionally, since our model is clothing-decoupled, we can exchange the clothes of avatars. Code are available on our project page https://hansenhuang0823.github.io/AvatarFusion.

cs.CV↗
arXiv2023

Action Sensitivity Learning for Temporal Action Localization

Temporal action localization (TAL), which involves recognizing and locating action instances, is a challenging task in video understanding. Most existing approaches directly predict action classes and regress offsets to boundaries, while overlooking the discrepant importance of each frame. In this paper, we propose an Action Sensitivity Learning framework (ASL) to tackle this task, which aims to assess the value of each frame and then leverage the generated action sensitivity to recalibrate the training procedure. We first introduce a lightweight Action Sensitivity Evaluator to learn the action sensitivity at the class level and instance level, respectively. The outputs of the two branches are combined to reweight the gradient of the two sub-tasks. Moreover, based on the action sensitivity of each frame, we design an Action Sensitive Contrastive Loss to enhance features, where the action-aware frames are sampled as positive pairs to push away the action-irrelevant frames. The extensive studies on various action localization benchmarks (i.e., MultiThumos, Charades, Ego4D-Moment Queries v1.0, Epic-Kitchens 100, Thumos14 and ActivityNet1.3) show that ASL surpasses the state-of-the-art in terms of average-mAP under multiple types of scenarios, e.g., single-labeled, densely-labeled and egocentric.

cs.CV↗
arXiv2023

Implications for the Explosion Mechanism of Type Ia Supernovae from their Late-time Spectra

Late-time spectra of Type Ia supernovae (SNe Ia) are important in clarifying the physics of their explosions, as they provide key clues to the inner structure of the exploding white dwarfs. We examined late-time optical spectra of 36 SNe Ia, including five from our own project (SNe 2019np, 2019ein, 2021hpr, 2021wuf, and 2022hrs), with phase coverage of $\sim 200$ to $\sim 400$ days after maximum light. At this late phase, the outer ejecta have become transparent and the features of inner iron-group elements emerge in the spectra. Based on multicomponent Gaussian fits and reasonable choices for the pseudocontinuum around Ni and Fe emission features, we get reliable estimates of the Ni to Fe ratio, which is sensitive to the explosion models of SNe Ia. Our results show that the majority (about 67%) of our SNe Ia are more consistent with the sub-Chandrasekhar-mass (i.e., double-detonation) model, although they could be affected by evolutionary or ionisation effects. Moreover, we find that the Si II $λ$6355 velocity measured around the time of maximum light tends to increase with the Ni to Fe ratio for the subsample with either redshifted or blueshifted nebular velocities, suggesting that progenitor metallicity might play an important role in accounting for the observed velocity diversity of SNe Ia.

astro-ph.HE↗
arXiv2023

Global optimization for the portfolio selection model with high-order moments

In this paper, we study the global optimality of polynomial portfolio optimization (PPO). The PPO is a kind of portfolio selection model with high-order moments and flexible risk preference parameters. We introduce a perturbation sample average approximation method, which can give a robust approximation of the PPO in form of linear conic optimization. The approximated problem can be solved globally with Moment-SOS relaxations. We summarize a semidefinite algorithm, which can be used to find reliable approximations of the optimal value and optimizer set of the PPO. Numerical examples are given to show the efficiency of the algorithm.

math.OC↗
arXiv2023

DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion

We present DiverseMotion, a new approach for synthesizing high-quality human motions conditioned on textual descriptions while preserving motion diversity.Despite the recent significant process in text-based human motion generation,existing methods often prioritize fitting training motions at the expense of action diversity. Consequently, striking a balance between motion quality and diversity remains an unresolved challenge. This problem is compounded by two key factors: 1) the lack of diversity in motion-caption pairs in existing benchmarks and 2) the unilateral and biased semantic understanding of the text prompt, focusing primarily on the verb component while neglecting the nuanced distinctions indicated by other words.In response to the first issue, we construct a large-scale Wild Motion-Caption dataset (WMC) to extend the restricted action boundary of existing well-annotated datasets, enabling the learning of diverse motions through a more extensive range of actions. To this end, a motion BLIP is trained upon a pretrained vision-language model, then we automatically generate diverse motion captions for the collected motion sequences. As a result, we finally build a dataset comprising 8,888 motions coupled with 141k text.To comprehensively understand the text command, we propose a Hierarchical Semantic Aggregation (HSA) module to capture the fine-grained semantics.Finally,we involve the above two designs into an effective Motion Discrete Diffusion (MDD) framework to strike a balance between motion quality and diversity. Extensive experiments on HumanML3D and KIT-ML show that our DiverseMotion achieves the state-of-the-art motion quality and competitive motion diversity. Dataset, code, and pretrained models will be released to reproduce all of our results.

cs.CV↗
arXiv2023

RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation

For robots to be useful outside labs and specialized factories we need a way to teach them new useful behaviors quickly. Current approaches lack either the generality to onboard new tasks without task-specific engineering, or else lack the data-efficiency to do so in an amount of time that enables practical use. In this work we explore dense tracking as a representational vehicle to allow faster and more general learning from demonstration. Our approach utilizes Track-Any-Point (TAP) models to isolate the relevant motion in a demonstration, and parameterize a low-level controller to reproduce this motion across changes in the scene configuration. We show this results in robust robot policies that can solve complex object-arrangement tasks such as shape-matching, stacking, and even full path-following tasks such as applying glue and sticking objects together, all from demonstrations that can be collected in minutes.

cs.RO↗
arXiv2023

TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement

We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence. Our approach employs two stages: (1) a matching stage, which independently locates a suitable candidate point match for the query point on every other frame, and (2) a refinement stage, which updates both the trajectory and query features based on local correlations. The resulting model surpasses all baseline methods by a significant margin on the TAP-Vid benchmark, as demonstrated by an approximate 20% absolute average Jaccard (AJ) improvement on DAVIS. Our model facilitates fast inference on long and high-resolution video sequences. On a modern GPU, our implementation has the capacity to track points faster than real-time, and can be flexibly extended to higher-resolution videos. Given the high-quality trajectories extracted from a large dataset, we demonstrate a proof-of-concept diffusion model which generates trajectories from static images, enabling plausible animations. Visualizations, source code, and pretrained models can be found on our project webpage.

cs.CV↗
arXiv2023

AIoT-Based Drum Transcription Robot using Convolutional Neural Networks

With the development of information technology, robot technology has made great progress in various fields. These new technologies enable robots to be used in industry, agriculture, education and other aspects. In this paper, we propose a drum robot that can automatically complete music transcription in real-time, which is based on AIoT and fog computing technology. Specifically, this drum robot system consists of a cloud node for data storage, edge nodes for real-time computing, and data-oriented execution application nodes. In order to analyze drumming music and realize drum transcription, we further propose a light-weight convolutional neural network model to classify drums, which can be more effectively deployed in terminal devices for fast edge calculations. The experimental results show that the proposed system can achieve more competitive performance and enjoy a variety of smart applications and services.

cs.RO↗
arXiv2023

Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation

Recent advances in semi-supervised semantic segmentation have been heavily reliant on pseudo labeling to compensate for limited labeled data, disregarding the valuable relational knowledge among semantic concepts. To bridge this gap, we devise LogicDiag, a brand new neural-logic semi-supervised learning framework. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. LogicDiag resolves such conflicts via reasoning with logic-induced diagnoses, enabling the recovery of (potentially) erroneous pseudo labels, ultimately alleviating the notorious error accumulation problem. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules. Extensive experiments on three standard semi-supervised semantic segmentation benchmarks demonstrate the effectiveness and generality of LogicDiag. Moreover, LogicDiag highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.

cs.CV↗
arXiv2023

Ground-based and JWST Observations of SN 2022pul: I. Unusual Signatures of Carbon, Oxygen, and Circumstellar Interaction in a Peculiar Type Ia Supernova

Nebular-phase observations of peculiar Type Ia supernovae (SNe Ia) provide important constraints on progenitor scenarios and explosion dynamics for both these rare SNe and the more common, cosmologically useful SNe Ia. We present observations from an extensive ground-based and space-based follow-up campaign to characterize SN 2022pul, a "super-Chandrasekhar" mass SN Ia (alternatively "03fg-like" SN), from before peak brightness to well into the nebular phase across optical to mid-infrared (MIR) wavelengths. The early rise of the light curve is atypical, exhibiting two distinct components, consistent with SN Ia ejecta interacting with dense carbon-oxygen rich circumstellar material (CSM). In the optical, SN 2022pul is most similar to SN 2012dn, having a low estimated peak luminosity ($M_{B}=-18.9$ mag) and high photospheric velocity relative to other 03fg-like SNe. In the nebular phase, SN 2022pul adds to the increasing diversity of the 03fg-like subclass. From 168 to 336 days after peak $B$-band brightness, SN 2022pul exhibits asymmetric and narrow emission from [O I] $λλ6300,\ 6364$ (${\rm FWHM} \approx 2{,}000$ km s$^{-1}$), strong, broad emission from [Ca II] $λλ7291,\ 7323$ (${\rm FWHM} \approx 7{,}300$ km s$^{-1}$), and a rapid Fe III to Fe II ionization change. Finally, we present the first-ever optical-to-mid-infrared (MIR) nebular spectrum of an 03fg-like SN Ia using data from JWST. In the MIR, strong lines of neon and argon, weak emission from stable nickel, and strong thermal dust emission (with $T \approx 500$ K), combined with prominent [O I] in the optical, suggest that SN 2022pul was produced by a white dwarf merger within carbon/oxygen-rich CSM.

astro-ph.HE↗
arXiv2023

Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigation

Audio-visual navigation is an audio-targeted wayfinding task where a robot agent is entailed to travel a never-before-seen 3D environment towards the sounding source. In this article, we present ORAN, an omnidirectional audio-visual navigator based on cross-task navigation skill transfer. In particular, ORAN sharpens its two basic abilities for a such challenging task, namely wayfinding and audio-visual information gathering. First, ORAN is trained with a confidence-aware cross-task policy distillation (CCPD) strategy. CCPD transfers the fundamental, point-to-point wayfinding skill that is well trained on the large-scale PointGoal task to ORAN, so as to help ORAN to better master audio-visual navigation with far fewer training samples. To improve the efficiency of knowledge transfer and address the domain gap, CCPD is made to be adaptive to the decision confidence of the teacher policy. Second, ORAN is equipped with an omnidirectional information gathering (OIG) mechanism, i.e., gleaning visual-acoustic observations from different directions before decision-making. As a result, ORAN yields more robust navigation behaviour. Taking CCPD and OIG together, ORAN significantly outperforms previous competitors. After the model ensemble, we got 1st in Soundspaces Challenge 2022, improving SPL and SR by 53% and 35% relatively.

cs.CV↗
arXiv2023

JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery

In this study, we focus on the problem of 3D human mesh recovery from a single image under obscured conditions. Most state-of-the-art methods aim to improve 2D alignment technologies, such as spatial averaging and 2D joint sampling. However, they tend to neglect the crucial aspect of 3D alignment by improving 3D representations. Furthermore, recent methods struggle to separate the target human from occlusion or background in crowded scenes as they optimize the 3D space of target human with 3D joint coordinates as local supervision. To address these issues, a desirable method would involve a framework for fusing 2D and 3D features and a strategy for optimizing the 3D space globally. Therefore, this paper presents 3D JOint contrastive learning with TRansformers (JOTR) framework for handling occluded 3D human mesh recovery. Our method includes an encoder-decoder transformer architecture to fuse 2D and 3D representations for achieving 2D$\&$3D aligned results in a coarse-to-fine manner and a novel 3D joint contrastive learning approach for adding explicitly global supervision for the 3D feature space. The contrastive learning approach includes two contrastive losses: joint-to-joint contrast for enhancing the similarity of semantically similar voxels (i.e., human joints), and joint-to-non-joint contrast for ensuring discrimination from others (e.g., occlusions and background). Qualitative and quantitative analyses demonstrate that our method outperforms state-of-the-art competitors on both occlusion-specific and standard benchmarks, significantly improving the reconstruction of occluded humans.

cs.CV↗