arXiv subjects

Xiaohao Xu

Publications and source records attributed to Xiaohao Xu.

58 records · Page 4Linked to original sources

arXiv2022

Towards Robust Video Object Segmentation with Adaptive Object Calibration

In the booming video era, video segmentation attracts increasing research attention in the multimedia community. Semi-supervised video object segmentation (VOS) aims at segmenting objects in all target frames of a video, given annotated object masks of reference frames. Most existing methods build pixel-wise reference-target correlations and then perform pixel-wise tracking to obtain target masks. Due to neglecting object-level cues, pixel-level approaches make the tracking vulnerable to perturbations, and even indiscriminate among similar objects. Towards robust VOS, the key insight is to calibrate the representation and mask of each specific object to be expressive and discriminative. Accordingly, we propose a new deep network, which can adaptively construct object representations and calibrate object masks to achieve stronger robustness. First, we construct the object representations by applying an adaptive object proxy (AOP) aggregation method, where the proxies represent arbitrary-shaped segments at multi-levels for reference. Then, prototype masks are initially generated from the reference-target correlations based on AOP. Afterwards, such proto-masks are further calibrated through network modulation, conditioning on the object proxy representations. We consolidate this conditional mask calibration process in a progressive manner, where the object representations and proto-masks evolve to be discriminative iteratively. Extensive experiments are conducted on the standard VOS benchmarks, YouTube-VOS-18/19 and DAVIS-17. Our model achieves the state-of-the-art performance among existing published works, and also exhibits superior robustness against perturbations. Our project repo is at https://github.com/JerryX1110/Robust-Video-Object-Segmentation

cs.CV↗

arXiv2022

Observation of high-order imaginary Poynting momentum optomechanics in structured light

The imaginary Poynting momentum (IPM) of light has been captivated an unusual origin of optomechanical effects on dipolar magnetoelectric particles, but yet observed in experiments. Here, we report, for the very first time, a whole family of high-order IPM forces for not only magnetoelectric but also generic Mie particles, assisted with their excited higher multipoles within. Such optomechanical phenomena derive from a nonlinear contribution of the IPM to the optical force, and can be remarkable even when the incident IPM is small. We observe the high-order optomechanics in a structured light beam with vortex-like IPM streamlines, which allows the low-order dipolar contribution to be suppressed. Our results provide the first unambiguous evidence of the ponderomotive nature of the IPM, expand the classification of optical forces and open new possibilities for optical forces and micromanipulations.

physics.optics↗

arXiv2021

Reliable Propagation-Correction Modulation for Video Object Segmentation

Error propagation is a general but crucial problem in online semi-supervised video object segmentation. We aim to suppress error propagation through a correction mechanism with high reliability. The key insight is to disentangle the correction from the conventional mask propagation process with reliable cues. We introduce two modulators, propagation and correction modulators, to separately perform channel-wise re-calibration on the target frame embeddings according to local temporal correlations and reliable references respectively. Specifically, we assemble the modulators with a cascaded propagation-correction scheme. This avoids overriding the effects of the reliable correction modulator by the propagation modulator. Although the reference frame with the ground truth label provides reliable cues, it could be very different from the target frame and introduce uncertain or incomplete correlations. We augment the reference cues by supplementing reliable feature patches to a maintained pool, thus offering more comprehensive and expressive object representations to the modulators. In addition, a reliability filter is designed to retrieve reliable patches and pass them in subsequent frames. Our model achieves state-of-the-art performance on YouTube-VOS18/19 and DAVIS17-Val/Test benchmarks. Extensive experiments demonstrate that the correction mechanism provides considerable performance gain by fully utilizing reliable guidance. Code is available at: https://github.com/JerryX1110/RPCMVOS.

cs.CV↗

arXiv2021

Reactive helicity and reactive power in nanoscale optics: Evanescent waves. Kerker conditions. Optical theorems and reactive dichroism

We put forward the complex helicity theorem. It constitutes a novel law that rules the build-up of the reactive helicity through its zero time-average flow. Its imaginary Poynting momentum accounts for the accretion of reactive power, are illustrated in: evanescent waves and fields scattered from magnetodielectric dipolar nanoparticles. As for the former, we show that its reactive helicity may be experimentally observed as we introduce a reactive spin momentum and a reactive orbital momentum in terms of which we express the imaginary field momentum, whose transversal component produces an optical force on a magnetoelectric particle that, as we illustrate, may surpass and can be discriminated from, the known force due to the so-called extraordinary momentum. We also uncover a non-conservative force on such a magnetoelectric particle, acting in the decay direction of the evanescent wave, and that may also be discriminated from the standard gradient force; thus making the reactive power of the wavefield also observable. Concerning the light scattered by magnetoelectric nanoparticles, we establish two optical theorems that govern the accretion of reactive helicity and reactive power on extinction of incident wave helicity and energy. Like a nule total -- internal plus external -- reactive power is at the root of a resonant scattered power, we show that a zero total reactive helicity underlies a resonant scattered helicity. The first Kerker condition, under which the particle becomes dual on illumination with circularly polarized light, we demonstrate to amount to a nule overall scattered reactive helicity. and emission. We discover a discriminatory property of the reactive helicity of chiral light incident on a chiral nanoparticle by excitation of the external reactive power. This for optical near-field enantiomeric separation, we call reactive dichroism.

physics.optics↗