No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models

To improve the viewer's Quality of Experience (QoE) and optimize computer graphics applications, 3D model quality assessment (3D-QA) has become an important task in the multimedia area. Point cloud and mesh are the two most widely used digital representation formats of 3D models, the visual quality of which is quite sensitive to lossy operations like simplification and compression. Therefore, many related studies such as point cloud quality assessment (PCQA) and mesh quality assessment (MQA) have been carried out to measure the caused visual quality degradations. However, a large part of previous studies utilizes full-reference (FR) metrics, which means they may fail to predict the quality level with the absence of the reference 3D model. Furthermore, few 3D-QA metrics are carried out to consider color information, which significantly restricts the effectiveness and scope of application. In this paper, we propose a no-reference (NR) quality assessment metric for colored 3D models represented by both point cloud and mesh. First, we project the 3D models from 3D space into quality-related geometry and color feature domains. Then, the natural scene statistics (NSS) and entropy are utilized to extract quality-aware features. Finally, the Support Vector Regressor (SVR) is employed to regress the quality-aware features into quality scores. Our method is mainly validated on the colored point cloud quality assessment database (SJTU-PCQA) and the colored mesh quality assessment database (CMDM). The experimental results show that the proposed method outperforms all the state-of-art NR 3D-QA metrics and obtains an acceptable gap with the state-of-art FR 3D-QA metrics.

MoDist: Motion Distillation for Self-supervised Video Representation Learning

We present MoDist as a novel method to explicitly distill motion information into self-supervised video representations. Compared to previous video representation learning methods that mostly focus on learning motion cues implicitly from RGB inputs, we show that the representation learned with our MoDist method focus more on foreground motion regions and thus generalizes better to downstream tasks. To achieve this, MoDist enriches standard contrastive learning objectives for RGB video clips with a cross-modal learning objective between a Motion pathway and a Visual pathway. We evaluate MoDist on several datasets for both action recognition (UCF101/HMDB51/SSv2) as well as action detection (AVA), and demonstrate state-of-the-art self-supervised performance on all datasets. Furthermore, we show that MoDist representation can be as effective as (in some cases even better than) representations learned with full supervision. Given its simplicity, we hope MoDist could serve as a strong baseline for future research in self-supervised video representation learning.

Neural Networks for Information Retrieval

Machine learning plays a role in many aspects of modern IR systems, and deep learning is applied in all of them. The fast pace of modern-day research has given rise to many different approaches for many different IR problems. The amount of information available can be overwhelming both for junior students and for experienced researchers looking for new research topics and directions. Additionally, it is interesting to see what key insights into IR problems the new technologies are able to give us. The aim of this full-day tutorial is to give a clear overview of current tried-and-trusted neural methods in IR and how they benefit IR research. It covers key architectures, as well as the most promising future directions.

Catchphrase: Automatic Detection of Cultural References

A snowclone is a customizable phrasal template that can be realized in multiple, instantly recognized variants. For example, ``* is the new *" (Orange is the new black, 40 is the new 30). Snowclones are extensively used in social media. In this paper, we study snowclones originating from pop-culture quotes; our goal is to automatically detect cultural references in text. We introduce a new, publicly available data set of pop-culture quotes and their corresponding snowclone usages and train models on them. We publish code for Catchphrase, an internet browser plugin to automatically detect and mark references in real-time, and examine its performance via a user study. Aside from assisting people to better comprehend cultural references, we hope that detecting snowclones can complement work on paraphrasing and help to tackle long-standing questions in social science about the dynamics of information propagation.

Non-Parametric Neuro-Adaptive Control Subject to Task Specifications

We develop a learning-based algorithm for the control of robotic systems governed by unknown, nonlinear dynamics to satisfy tasks expressed as signal temporal logic specifications. Most existing algorithms either assume certain parametric forms for the dynamic terms or resort to unnecessarily large control inputs (e.g., using reciprocal functions) in order to provide theoretical guarantees. The proposed algorithm avoids the aforementioned drawbacks by innovatively integrating neural network-based learning with adaptive control. More specifically, the algorithm learns a controller, represented as a neural network, using training data that correspond to a collection of different tasks and robot parameters. It then incorporates this neural network into an online closed-loop adaptive control mechanism in such a way that the resulting behavior satisfies a user-defined task. The proposed algorithm does not use any information on the unknown dynamic terms or any approximation schemes. We provide formal theoretical guarantees on the satisfaction of the task and we demonstrate the effectiveness of the algorithm in a virtual simulator using a 6-DOF robotic manipulator.

Frequency-packed Faster-than-Nyquist Signaling via Symbol-level Precoding for Multi-user MISO Redundant Transmissions

This work addresses the issue of interference generated by co-channel users in downlink multi-antenna multicarrier systems with frequency-packed faster-than-Nyquist (FTN) signaling. The resulting interference stems from an aggressive strategy for enhancing the throughput via frequency reuse across different users and the squeezing of signals in the time-frequency plane beyond the Nyquist limit. The error-free spectral efficiency is proved to be increasing with the frequency packing and FTN acceleration factors. The lower bound for the FTN sampling period that guarantees information losslesness is derived as a function of the transmitting-filter roll-off factor, the frequency-packing factor, and the number of subcarriers. Space-time-frequency symbol-level precoders (SLPs) that trade off constructive and destructive interblock interference (IBI) at the single-antenna user terminals are proposed. Redundant elements are added as guard interval to cope with vestigial destructive IBI effects. The proposals can handle channels with delay spread longer than the multicarrier-symbol duration. The receiver architecture is simple, for it does not require digital multicarrier demodulation. Simulations indicate that the proposed SLP outperforms zero-forcing precoding and achieves a target balance between spectral and energy efficiencies by controlling the amount of added redundancy from zero (full IBI) to half (destructive IBI-free) the group delay of the equivalent channel.

Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performance

Generally speaking, the main objective when training a neural speech synthesis system is to synthesize natural and expressive speech from the output layer of the neural network without much attention given to the hidden layers. However, by learning useful latent representation, the system can be used for many more practical scenarios. In this paper, we investigate the use of quantized vectors to model the latent linguistic embedding and compare it with the continuous counterpart. By enforcing different policies over the latent spaces in the training, we are able to obtain a latent linguistic embedding that takes on different properties while having a similar performance in terms of quality and speaker similarity. Our experiments show that the voice cloning system built with vector quantization has only a small degradation in terms of perceptive evaluations, but has a discrete latent space that is useful for reducing the representation bit-rate, which is desirable for data transferring, or limiting the information leaking, which is important for speaker anonymization and other tasks of that nature.

Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL

There is considerable interest in designing meta-reinforcement learning (meta-RL) algorithms, which enable autonomous agents to adapt new tasks from small amount of experience. In meta-RL, the specification (such as reward function) of current task is hidden from the agent. In addition, states are hidden within each task owing to sensor noise or limitations in realistic environments. Therefore, the meta-RL agent faces the challenge of specifying both the hidden task and states based on small amount of experience. To address this, we propose estimating disentangled belief about task and states, leveraging an inductive bias that the task and states can be regarded as global and local features of each task. Specifically, we train a hierarchical state-space model (HSSM) parameterized by deep neural networks as an environment model, whose global and local latent variables correspond to task and states, respectively. Because the HSSM does not allow analytical computation of posterior distribution, i.e., belief, we employ amortized inference to approximate it. After the belief is obtained, we can augment observations of a model-free policy with the belief to efficiently train the policy. Moreover, because task and state information are factorized and interpretable, the downstream policy training is facilitated compared with the prior methods that did not consider the hierarchical nature. Empirical validations on a GridWorld environment confirm that the HSSM can separate the hidden task and states information. Then, we compare the meta-RL agent with the HSSM to prior meta-RL methods in MuJoCo environments, and confirm that our agent requires less training data and reaches higher final performance.

Learning Multi-Level Information for Dialogue Response Selection by Highway Recurrent Transformer

With the increasing research interest in dialogue response generation, there is an emerging branch formulating this task as selecting next sentences, where given the partial dialogue contexts, the goal is to determine the most probable next sentence. Following the recent success of the Transformer model, this paper proposes (1) a new variant of attention mechanism based on multi-head attention, called highway attention, and (2) a recurrent model based on transformer and the proposed highway attention, so-called Highway Recurrent Transformer. Experiments on the response selection task in the seventh Dialog System Technology Challenge (DSTC7) show the capability of the proposed model of modeling both utterance-level and dialogue-level information; the effectiveness of each module is further analyzed as well.

Data Sharing Markets

With the growing use of distributed machine learning techniques, there is a growing need for data markets that allows agents to share data with each other. Nevertheless data has unique features that separates it from other commodities including replicability, cost of sharing, and ability to distort. We study a setup where each agent can be both buyer and seller of data. For this setup, we consider two cases: bilateral data exchange (trading data with data) and unilateral data exchange (trading data with money). We model bilateral sharing as a network formation game and show the existence of strongly stable outcome under the top agents property by allowing limited complementarity. We propose ordered match algorithm which can find the stable outcome in O(N^2) (N is the number of agents). For the unilateral sharing, under the assumption of additive cost structure, we construct competitive prices that can implement any social welfare maximizing outcome. Finally for this setup when agents have private information, we propose mixed-VCG mechanism which uses zero cost data distortion of data sharing with its isolated impact to achieve budget balance while truthfully implementing socially optimal outcomes to the exact level of budget imbalance of standard VCG mechanisms. Mixed-VCG uses data distortions as data money for this purpose. We further relax zero cost data distortion assumption by proposing distorted-mixed-VCG. We also extend our model and results to data sharing via incremental inquiries and differential privacy costs.