A variational approach for estimation of monocular depth and camera motion in autonomous driving

In this paper, a new direct computational approach to dense 3D reconstruction in autonomous driving is proposed to simultaneously estimate the depth and the camera motion for the motion stereo problem. A traditional Structure from Motion framework is utilized to establish geometric constrains for our variational model. The architecture is mainly composed of the texture constancy constraint, one-order motion smoothness constraint, a second-order depth regularize constraint and a soft constraint. The texture constancy constraint can improve the robustness against illumination changes. One-order motion smoothness constraint can reduce the noise in estimation of dense correspondence. The depth regularize constraint is used to handle inherent ambiguities and guarantee a smooth or piecewise smooth surface, and the soft constraint can provide a dense correspondence as initial estimation of the camera matrix to improve the robustness future. Compared to the traditional dense Structure from Motion approaches and popular stereo approaches, our monocular depth estimation results are more accurate and more robust. Even in contrast to the popular depth from single image networks, our variational approach still has good performance in estimation of monocular depth and camera motion.

Inductive Contextual Relation Learning for Personalization

Web personalization, e.g., recommendation or relevance search, tailoring a service/product to accommodate specific online users, is becoming increasingly important. Inductive personalization aims to infer the relations between existing entities and unseen new ones, e.g., searching relevant authors for new papers or recommending new items to users. This problem, however, is challenging since most of recent studies focus on transductive problem for existing entities. In addition, despite some inductive learning approaches have been introduced recently, their performance is sub-optimal due to relatively simple and inflexible architectures for aggregating entity’s content. To this end, we propose the inductive contextual personalization (ICP) framework through contextual relation learning. Specifically, we first formulate the pairwise relations between entities with a ranking optimization scheme that employs neural aggregator to fuse entity’s heterogeneous contents. Next, we introduce a node embedding term to capture entity’s contextual relations, as a smoothness constraint over the prior ranking objective. Finally, the gradient descent procedure with adaptive negative sampling is employed to learn the model parameters. The learned model is capable of inferring the relations between existing entities and inductive ones. Thorough experiments demonstrate that ICP outperforms numerous baseline methods for two different applications, i.e., relevant author search and new item recommendation.

Best Arm Identification in Spectral Bandits

We study best-arm identification with fixed confidence in bandit models with graph smoothness constraint. We provide and analyze an efficient gradient ascent algorithm to compute the sample complexity of this problem as a solution of a non-smooth max-min problem (providing in passing a simplified analysis for the unconstrained case). Building on this algorithm, we propose an asymptotically optimal strategy. We furthermore illustrate by numerical experiments both the strategy's efficiency and the impact of the smoothness constraint on the sample complexity. Best Arm Identification (BAI) is an important challenge in many applications ranging from parameter tuning to clinical trials. It is now very well understood in vanilla bandit models, but real-world problems typically involve some dependency between arms that requires more involved models. Assuming a graph structure on the arms is an elegant practical way to encompass this phenomenon, but this had been done so far only for regret minimization. Addressing BAI with graph constraints involves delicate optimization problems for which the present paper offers a solution.

Least-squares decomposition with time–space constraint for denoising microseismic data

SUMMARY Microseismic data are usually of low signal-to-noise ratio (SNR), which makes it difficult to utilize the microseismic waveforms for imaging and inversion. We develop a useful denoising algorithm based on a non-stationary least-squares decomposition model to enhance the quality of microseismic signals. The microseismic signals are assumed to be represented by a superposition of several smoothly variable components. We construct a least-squares inverse problem to solve for the the smooth components. We constrain the least-squares inversion via both time and space constraints. The temporal smoothness constraint is applied to ensure the stability when calculating the non-stationary autoregression coefficients. The space-smoothness constraint is applied to extract the spatial correlation among multichannel microseismic traces. The new algorithm is validated via several synthetic and real microseismic data and are proved to be effective. Comparison with the state-of-the-art algorithms demonstrates that the proposed method is more powerful in suppressing random noise of a wide range of levels than its competing methods.

Adaptive Smoothness Constraint Ionospheric Tomography Algorithm

Ionospheric tomography reconstruction based on global navigation satellite system observations is usually an ill-posed problem. To resolve it, an adaptive smoothness constraint ionospheric tomography algorithm is proposed in this work. The new algorithm performs an adaptive adjustment for the constrained weight coefficients of the tomography system. The computational efficiency and the reconstructed quality of ionospheric imaging are improved by using the new algorithm. A numerical simulation experiment was conducted in order to validate the feasibility and superiority of the algorithm. The statistical results of the reconstructed errors and the comparisons of ionospheric profiles confirmed the superiority of the new algorithm. Finally, the new algorithm was successfully applied to reconstruct three-dimensional ionospheric images under geomagnetic quiet and geomagnetic disturbance conditions over Hunan province. The tomographic results are reasonable and consistent with the general behavior of the ionosphere. The positive and negative phase storm effects are found during geomagnetic storm occurrence.