Search arXiv⌕ Search

arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 703 records · Page 39Linked to original sources
arXiv2023

Minute-Cadence Observations of the LAMOST Fields with the TMTS: II. Catalogues of Short-Period Variable Stars from the First Two-Year Surveys

Over the past few years, wide-field time-domain surveys like ZTF and OGLE have led to discoveries of various types of interesting short-period stellar variables, such as ultracompact eclipsing binary white dwarfs, rapidly rotating magnetised white dwarfs (WDs), transitional cataclysmic variables between hydrogen-rich and helium accretion, and blue large-amplitude pulsators (BLAPs), which greatly enrich our understandings of stellar physics under some extreme conditions. In this paper, we report the first-two-year discoveries of short-period variables (i.e., P<2 hr) by the Tsinghua University-Ma Huateng Telescopes for Survey (TMTS). TMTS is a multi-tube telescope system with a field of view up to 18 deg^2, which started to monitor the LAMOST sky areas since 2020 and generated uninterrupted minute-cadence light curves for about ten million sources within 2 years. Adopting the Lomb-Scargle periodogram with period-dependent thresholds for the maximum powers, we identify over 1 100 sources that exhibit a variation period shorter than 2 hr. Compiling the light curves with the Gaia magnitudes and colours, LAMOST spectral parameters, VSX classifications, and archived observations from other prevailing time-domain survey missions, we identified 1 076 as delta Scuti stars, which allows us study their populations and physical properties in the short-period regime. The other 31 sources include BLAPs, subdwarf B variables (sdBVs), pulsating WDs, ultracompact/short-period eclipsing/ellipsoidal binaries, cataclysmic variables below the period gap, etc., which are highly interesting and worthy of follow-up investigations.

astro-ph.SR↗
arXiv2023

TAP-Vid: A Benchmark for Tracking Any Point in a Video

Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move. This information is useful to make inferences about 3D shape, physical properties and object interactions. While the problem of tracking arbitrary physical points on surfaces over longer video clips has received some attention, no dataset or benchmark for evaluation existed, until now. In this paper, we first formalize the problem, naming it tracking any point (TAP). We introduce a companion benchmark, TAP-Vid, which is composed of both real-world videos with accurate human annotations of point tracks, and synthetic videos with perfect ground-truth point tracks. Central to the construction of our benchmark is a novel semi-automatic crowdsourced pipeline which uses optical flow estimates to compensate for easier, short-term motion like camera shake, allowing annotators to focus on harder sections of video. We validate our pipeline on synthetic data and propose a simple end-to-end point tracking model TAP-Net, showing that it outperforms all prior methods on our benchmark when trained on synthetic data.

cs.CV↗
arXiv2023

Joint Video Multi-Frame Interpolation and Deblurring under Unknown Exposure Time

Natural videos captured by consumer cameras often suffer from low framerate and motion blur due to the combination of dynamic scene complexity, lens and sensor imperfection, and less than ideal exposure setting. As a result, computational methods that jointly perform video frame interpolation and deblurring begin to emerge with the unrealistic assumption that the exposure time is known and fixed. In this work, we aim ambitiously for a more realistic and challenging task - joint video multi-frame interpolation and deblurring under unknown exposure time. Toward this goal, we first adopt a variant of supervised contrastive learning to construct an exposure-aware representation from input blurred frames. We then train two U-Nets for intra-motion and inter-motion analysis, respectively, adapting to the learned exposure representation via gain tuning. We finally build our video reconstruction network upon the exposure and motion representation by progressive exposure-adaptive convolution and motion refinement. Extensive experiments on both simulated and real-world datasets show that our optimized method achieves notable performance gains over the state-of-the-art on the joint video x8 interpolation and deblurring task. Moreover, on the seemingly implausible x16 interpolation task, our method outperforms existing methods by more than 1.5 dB in terms of PSNR.

cs.CV↗
arXiv2023

CRRS: Concentric Rectangles Regression Strategy for Multi-point Representation on Fisheye Images

Modern object detectors take advantage of rectangular bounding boxes as a conventional way to represent objects. When it comes to fisheye images, rectangular boxes involve more background noise rather than semantic information. Although multi-point representation has been proposed, both the regression accuracy and convergence still perform inferior to the widely used rectangular boxes. In order to further exploit the advantages of multi-point representation for distorted images, Concentric Rectangles Regression Strategy(CRRS) is proposed in this work. We adopt smoother mean loss to allocate weights and discuss the effect of hyper-parameter to prediction results. Moreover, an accurate pixel-level method is designed to obtain irregular IoU for estimating detector performance. Compared with the previous work for muti-point representation, the experiments show that CRRS can improve the training performance both in accurate and stability. We also prove that multi-task weighting strategy facilitates regression process in this design.

cs.CV↗
arXiv2023

Sector Patch Embedding: An Embedding Module Conforming to The Distortion Pattern of Fisheye Image

Fisheye cameras suffer from image distortion while having a large field of view(LFOV). And this fact leads to poor performance on some fisheye vision tasks. One of the solutions is to optimize the current vision algorithm for fisheye images. However, most of the CNN-based methods and the Transformer-based methods lack the capability of leveraging distortion information efficiently. In this work, we propose a novel patch embedding method called Sector Patch Embedding(SPE), conforming to the distortion pattern of the fisheye image. Furthermore, we put forward a synthetic fisheye dataset based on the ImageNet-1K and explore the performance of several Transformer models on the dataset. The classification top-1 accuracy of ViT and PVT is improved by 0.75% and 2.8% with SPE respectively. The experiments show that the proposed sector patch embedding method can better perceive distortion and extract features on the fisheye images. Our method can be easily adopted to other Transformer-based models. Source code is at https://github.com/IN2-ViAUn/Sector-Patch-Embedding.

cs.CV↗
arXiv2023

Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation

Video-based 3D human pose and shape estimations are evaluated by intra-frame accuracy and inter-frame smoothness. Although these two metrics are responsible for different ranges of temporal consistency, existing state-of-the-art methods treat them as a unified problem and use monotonous modeling structures (e.g., RNN or attention-based block) to design their networks. However, using a single kind of modeling structure is difficult to balance the learning of short-term and long-term temporal correlations, and may bias the network to one of them, leading to undesirable predictions like global location shift, temporal inconsistency, and insufficient local details. To solve these problems, we propose to structurally decouple the modeling of long-term and short-term correlations in an end-to-end framework, Global-to-Local Transformer (GLoT). First, a global transformer is introduced with a Masked Pose and Shape Estimation strategy for long-term modeling. The strategy stimulates the global transformer to learn more inter-frame correlations by randomly masking the features of several frames. Second, a local transformer is responsible for exploiting local details on the human mesh and interacting with the global transformer by leveraging cross-attention. Moreover, a Hierarchical Spatial Correlation Regressor is further introduced to refine intra-frame estimations by decoupled global-local representation and implicit kinematic constraints. Our GLoT surpasses previous state-of-the-art methods with the lowest model parameters on popular benchmarks, i.e., 3DPW, MPI-INF-3DHP, and Human3.6M. Codes are available at https://github.com/sxl142/GLoT.

cs.CV↗
arXiv2023

Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models

Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such powerful VLMs is a promising direction for building effective video recognition models. However, current exploration in this field is still limited. We believe that the greatest value of pre-trained VLMs lies in building a bridge between visual and textual domains. In this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video Attribute Association mechanism, which leverages the Video-to-Text knowledge to generate textual auxiliary attributes for complementing video recognition. ii) We also present a Temporal Concept Spotting mechanism that uses the Text-to-Video expertise to capture temporal saliency in a parameter-free manner, leading to enhanced video representation. Extensive studies on six popular video datasets, including Kinetics-400 & 600, UCF-101, HMDB-51, ActivityNet and Charades, show that our method achieves state-of-the-art performance in various recognition scenarios, such as general, zero-shot, and few-shot video recognition. Our best model achieves a state-of-the-art accuracy of 88.6% on the challenging Kinetics-400 using the released CLIP model. The code is available at https://github.com/whwu95/BIKE .

cs.CV↗
arXiv2023

Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning

Current video-based scene graph generation (VidSGG) methods have been found to perform poorly on predicting predicates that are less represented due to the inherent biased distribution in the training data. In this paper, we take a closer look at the predicates and identify that most visual relations (e.g. sit_above) involve both actional pattern (sit) and spatial pattern (above), while the distribution bias is much less severe at the pattern level. Based on this insight, we propose a decoupled label learning (DLL) paradigm to address the intractable visual relation prediction from the pattern-level perspective. Specifically, DLL decouples the predicate labels and adopts separate classifiers to learn actional and spatial patterns respectively. The patterns are then combined and mapped back to the predicate. Moreover, we propose a knowledge-level label decoupling method to transfer non-target knowledge from head predicates to tail predicates within the same pattern to calibrate the distribution of tail classes. We validate the effectiveness of DLL on the commonly used VidSGG benchmark, i.e. VidVRD. Extensive experiments demonstrate that the DLL offers a remarkably simple but highly effective solution to the long-tailed problem, achieving the state-of-the-art VidSGG performance.

cs.CV↗
arXiv2023

Probing hairy black holes caused by gravitational decoupling using quasinormal modes and greybody bounds

Gravitational decoupling can add hair to the black holes by adding extra sources. The quasinormal modes of hairy black hole caused by gravitational decoupling for the massless scalar field, electromagnetic field, and gravitational perturbation are investigated. The equations of effective potential for three perturbations are derived in hairy black hole spacetime. We also study the time evolution corresponding to the three perturbations, and the quasinormal mode frequencies are calculated using the Prony method through the time-domain profiles. By analyzing the influence of the hairs ($α$, $l_0$ and $Q$) for the black holes we studying on quasinormal mode, we find that the hairs $α$ and $l_0$ decrease the oscillation frequency of the gravitational wave signal, and the hair $Q$ increase its oscillation frequency.Furthermore, we have calculated the bounds of greybody factor and high-energy absorption cross section with the Sinc approximation, which reveals that the presence of charges ($α$ and $l_0$) generating primary hair can increase the probability of gravitational radiation arriving spatial infinity, whereas the charge $Q$ from the extra sources does the opposite.

gr-qc↗
arXiv2023

Landauer-QFLPS model for mixed Schottky-Ohmic contact two-dimensional transistors

Two-dimensional material-based field effect transistors (2DM-FETs) are playing a revolutionary role in electronic devices. However, after years of development, no device model can match the Pao-Sah model for standard silicon-based transistors in terms of physical accuracy and computational efficiency to support large-scale integrated circuit design. One remaining critical obstacle is the contacts of 2DM-FETs. In order to self-consistently include the contact effect in the current model, it is necessary to perform self-consistent calculations, which is a fatal flaw for applications that prioritize efficiency. Here, we report that the Landauer-QFLPS model effectively overcomes the above contradiction, where QFLPS means quasi-Fermi-level phase space theory. By connecting the physical pictures of the contact and the intrinsic channel part, we have successfully derived a drain-source current formula including the contact effect. To verify the model, we prepared transistors based on two typical 2DMs, black phosphorus (BP) and molybdenum disulfide (MoS2), the former having ambipolar transport and the latter showing electron-dominant unipolar transport. The proposed new formula could describe both 2DM-FETs with Schottky or Ohmic contacts. Moreover, compared with traditional methods, the proposed model has the advantages of accuracy and efficiency, especially in describing non-monotonic drain conductance characteristics, because the contact effect is self-consistently and compactly packaged as an exponential term. More importantly, we also examined the model at the circuit level. Here, we fabricated a three-bit threshold inverter quantizer circuit based on ambipolar-BP process and experimentally demonstrated that the model can accurately predict the circuit performance. This industry-benign 2DM-FET model is supposed to be very useful for the development of 2DM-FET-based integrated circuits.

physics.app-ph↗
arXiv2023

Exploring Expression-related Self-supervised Learning for Affective Behaviour Analysis

This paper explores an expression-related self-supervised learning (SSL) method (ContraWarping) to perform expression classification in the 5th Affective Behavior Analysis in-the-wild (ABAW) competition. Affective datasets are expensive to annotate, and SSL methods could learn from large-scale unlabeled data, which is more suitable for this task. By evaluating on the Aff-Wild2 dataset, we demonstrate that ContraWarping outperforms most existing supervised methods and shows great application potential in the affective analysis area. Codes will be released on: https://github.com/youqingxiaozhua/ABAW5.

cs.CV↗
arXiv2023

Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation

The objective of this paper is self-supervised learning of video object segmentation. We develop a unified framework which simultaneously models cross-frame dense correspondence for locally discriminative feature learning and embeds object-level context for target-mask decoding. As a result, it is able to directly learn to perform mask-guided sequential segmentation from unlabeled videos, in contrast to previous efforts usually relying on an oblique solution - cheaply "copying" labels according to pixel-wise correlations. Concretely, our algorithm alternates between i) clustering video pixels for creating pseudo segmentation labels ex nihilo; and ii) utilizing the pseudo labels to learn mask encoding and decoding for VOS. Unsupervised correspondence learning is further incorporated into this self-taught, mask embedding scheme, so as to ensure the generic nature of the learnt representation and avoid cluster degeneracy. Our algorithm sets state-of-the-arts on two standard benchmarks (i.e., DAVIS17 and YouTube-VOS), narrowing the gap between self- and fully-supervised VOS, in terms of both performance and network architecture design.

cs.CV↗
arXiv2023

Unsupervised Facial Expression Representation Learning with Contrastive Local Warping

This paper investigates unsupervised representation learning for facial expression analysis. We think Unsupervised Facial Expression Representation (UFER) deserves exploration and has the potential to address some key challenges in facial expression analysis, such as scaling, annotation bias, the discrepancy between discrete labels and continuous emotions, and model pre-training. Such motivated, we propose a UFER method with contrastive local warping (ContraWarping), which leverages the insight that the emotional expression is robust to current global transformation (affine transformation, color jitter, etc.) but can be easily changed by random local warping. Therefore, given a facial image, ContraWarping employs some global transformations and local warping to generate its positive and negative samples and sets up a novel contrastive learning framework. Our in-depth investigation shows that: 1) the positive pairs from global transformations may be exploited with general self-supervised learning (e.g., BYOL) and already bring some informative features, and 2) the negative pairs from local warping explicitly introduce expression-related variation and further bring substantial improvement. Based on ContraWarping, we demonstrate the benefit of UFER under two facial expression analysis scenarios: facial expression recognition and image retrieval. For example, directly using ContraWarping features for linear probing achieves 79.14% accuracy on RAF-DB, significantly reducing the gap towards the full-supervised counterpart (88.92% / 84.81% with/without pre-training).

cs.CV↗
arXiv2023

Ringing and echoes from black bounces surrounded by the string cloud

In the string theory, the fundamental blocks of nature are not particles but one-dimensional strings. Therefore, a generalization of this idea is to think of it as a cloud of strings. Rodrigues et al. embedded the black bounces spacetime into the string cloud, which demonstrates that the existence of the string cloud makes the Bardeen black hole singular, while the black bounces spacetime remains regular. On the other hand, the echoes are the correction to the late stage of the quasinormal ringing for a black hole, which is caused by the deviation of the spacetime relative to the initial black hole spacetime geometry in the near-horizon region. In this work, we study the gravitational wave echoes of black bounces spacetime surrounded by a cloud of strings under scalar field and electromagnetic field perturbation to explore the effects caused by a string cloud in the near-horizon region. The ringing of the regular black hole and traversable wormhole with string cloud are presented. Our results demonstrate that the black bounce spacetime with strings cloud is characterized by gravitational wave echoes as it transitions from regular black holes to wormholes, i.e. the echoes signal will facilitate us to distinguish between black holes and the wormholes in black bounces surrounded by the string cloud.

gr-qc↗
arXiv2023

Lana: A Language-Capable Navigator for Instruction Following and Generation

Recently, visual-language navigation (VLN) -- entailing robot agents to follow navigation instructions -- has shown great advance. However, existing literature put most emphasis on interpreting instructions into actions, only delivering "dumb" wayfinding agents. In this article, we devise LANA, a language-capable navigation agent which is able to not only execute human-written navigation commands, but also provide route descriptions to humans. This is achieved by simultaneously learning instruction following and generation with only one single model. More specifically, two encoders, respectively for route and language encoding, are built and shared by two decoders, respectively, for action prediction and instruction generation, so as to exploit cross-task knowledge and capture task-specific characteristics. Throughout pretraining and fine-tuning, both instruction following and generation are set as optimization objectives. We empirically verify that, compared with recent advanced task-specific solutions, LANA attains better performances on both instruction following and route description, with nearly half complexity. In addition, endowed with language generation capability, LANA can explain to humans its behaviors and assist human's wayfinding. This work is expected to foster future efforts towards building more trustworthy and socially-intelligent navigation robots.

cs.CV↗
arXiv2023

An efficient model algorithm for two-dimensional field-effect transistors

Two-dimensional materials-based field-effect transistors (2DM-FETs) exhibit both ambipolar and unipolar transport types. To physically and compactly cover both cases, we put forward a quasi-Fermi-level phase space (QFLPS) approach to model the ambipolar effect in our previous work. This work aims to further improve the QFLPS model's numerical aspect so that the model can be implanted into the standard circuit simulator. We first rigorously derive the integral-free formula for the drain-source current to achieve this goal. It is more friendly to computation than the integral form. Besides, it explicitly gives the correlation terms between the electron and hole components. Secondly, to work out the boundary values required by the new expressions, we develop a fast evaluation algorithm for the surface electrostatic potential based on the zero-temperature limit property of the 2DM-FET system. By calibrating the model with the realistic device data of black phosphorus (BP) and monolayer molybdenum disulfide (ML-MoS2) FETs, the completed algorithm is tested against practical cases. The results show a typical superiority to the benchmark algorithm by two orders of magnitude in time consumption can be achieved while keeping a high accuracy with 7 to 9 significant digits.

cond-mat.mtrl-sci↗
arXiv2023

3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective

This research aims to study a self-supervised 3D clothing reconstruction method, which recovers the geometry shape and texture of human clothing from a single image. Compared with existing methods, we observe that three primary challenges remain: (1) 3D ground-truth meshes of clothing are usually inaccessible due to annotation difficulties and time costs; (2) Conventional template-based methods are limited to modeling non-rigid objects, e.g., handbags and dresses, which are common in fashion images; (3) The inherent ambiguity compromises the model training, such as the dilemma between a large shape with a remote camera or a small shape with a close camera. In an attempt to address the above limitations, we propose a causality-aware self-supervised learning method to adaptively reconstruct 3D non-rigid objects from 2D images without 3D annotations. In particular, to solve the inherent ambiguity among four implicit variables, i.e., camera position, shape, texture, and illumination, we introduce an explainable structural causal map (SCM) to build our model. The proposed model structure follows the spirit of the causal map, which explicitly considers the prior template in the camera estimation and shape prediction. When optimization, the causality intervention tool, i.e., two expectation-maximization loops, is deeply embedded in our algorithm to (1) disentangle four encoders and (2) facilitate the prior template. Extensive experiments on two 2D fashion benchmarks (ATR and Market-HQ) show that the proposed method could yield high-fidelity 3D reconstruction. Furthermore, we also verify the scalability of the proposed method on a fine-grained bird dataset, i.e., CUB. The code is available at https://github.com/layumi/ 3D-Magic-Mirror .

cs.CV↗