Learning effective motion features is an essential pursuit of video representation learning. This paper presents a simple yet effective sample construction strategy to boost the learning of motion features in video contrastive learning. The proposed method, dubbed Motion-focused Quadruple Construction (MoQuad), augments the instance discrimination by meticulously disturbing the appearance and motion of both the positive and negative samples to create a quadruple for each video instance, such that the model is encouraged to exploit motion information. Unlike recent approaches that create extra auxiliary tasks for learning motion features or apply explicit temporal modelling, our method keeps the simple and clean contrastive learning paradigm (i.e.,SimCLR) without multi-task learning or extra modelling. In addition, we design two extra training strategies by analyzing initial MoQuad experiments. By simply applying MoQuad to SimCLR, extensive experiments show that we achieve superior performance on downstream tasks compared to the state of the arts. Notably, on the UCF-101 action recognition task, we achieve 93.7% accuracy after pre-training the model on Kinetics-400 for only 200 epochs, surpassing various previous methods
This volume contains revised versions of the papers selected for the third volume of the Online Handbook of Argumentation for AI (OHAAI). Previously, formal theories of argument and argument interaction have been proposed and studied, and this has led to the more recent study of computational models of argument. Argumentation, as a field within artificial intelligence (AI), is highly relevant for researchers interested in symbolic representations of knowledge and defeasible reasoning. The purpose of this handbook is to provide an open access and curated anthology for the argumentation research community. OHAAI is designed to serve as a research hub to keep track of the latest and upcoming PhD-driven research on the theory and application of argumentation in all areas related to AI.
As the Internet developed rapidly, it is important to choose suitable web services from a wide range of candidates. Quality of service (QoS) describes the performance of a web service dynamically with respect to the service requested by the service consumer. Moreover, the latent factorization of tenors (LFT) is very effective for discovering temporal patterns in high dimensional and sparse (HiDS) tensors. However, current LFT models suffer from a low convergence rate and rarely account for the effects of outliers. To address the above problems, this paper proposes an Alternating direction method of multipliers (ADMM)-based Outlier-Resilient Nonnegative Latent-factorization of Tensors model. We maintain the non-negativity of the model by constructing an augmented Lagrangian function with the ADMM optimization framework. In addition, the Cauchy function is taken as the metric function to reduce the impact on the model training. The empirical work on two dynamic QoS datasets shows that the proposed method has faster convergence and better performance on prediction accuracy.
In this work, we propose a novel paradigm to encode the position of targets for target tracking in videos using transformers. The proposed paradigm, Dense Spatio-Temporal (DST) position encoding, encodes spatio-temporal position information in a pixel-wise dense fashion. The provided position encoding provides location information to associate targets across frames beyond appearance matching by comparing objects in two bounding boxes. Compared to the typical transformer positional encoding, our proposed encoding is applied to the 2D CNN features instead of the projected feature vectors to avoid losing positional information. Moreover, the designed DST encoding can represent the location of a single-frame object and the evolution of the location of the trajectory among frames uniformly. Integrated with the DST encoding, we build a transformer-based multi-object tracking model. The model takes a video clip as input and conducts the target association in the clip. It can also perform online inference by associating existing trajectories with objects from the new-coming frames. Experiments on video multi-object tracking (MOT) and multi-object tracking and segmentation (MOTS) datasets demonstrate the effectiveness of the proposed DST position encoding.
Predictive learning uses a known state to generate a future state over a period of time. It is a challenging task to predict spatiotemporal sequence because the spatiotemporal sequence varies both in time and space. The mainstream method is to model spatial and temporal structures at the same time using RNN-based or transformer-based architecture, and then generates future data by using learned experience in the way of auto-regressive. The method of learning spatial and temporal features simultaneously brings a lot of parameters to the model, which makes the model difficult to be convergent. In this paper, a modular design is proposed, which decomposes spatiotemporal sequence model into two modules: a spatial encoder-decoder and a predictor. These two modules can extract spatial features and predict future data respectively. The spatial encoder-decoder maps the data into a latent embedding space and generates data from the latent space while the predictor forecasts future embedding from past. By applying the design to the current research and performing experiments on KTH-Action and MovingMNIST datasets, we both improve computational performance and obtain state-of-the-art results.
FP8 is a natural progression for accelerating deep learning training inference beyond the 16-bit formats common in modern processors. In this paper we propose an 8-bit floating point (FP8) binary interchange format consisting of two encodings - E4M3 (4-bit exponent and 3-bit mantissa) and E5M2 (5-bit exponent and 2-bit mantissa). While E5M2 follows IEEE 754 conventions for representatio of special values, E4M3's dynamic range is extended by not representing infinities and having only one mantissa bit-pattern for NaNs. We demonstrate the efficacy of the FP8 format on a variety of image and language tasks, effectively matching the result quality achieved by 16-bit training sessions. Our study covers the main modern neural network architectures - CNNs, RNNs, and Transformer-based models, leaving all the hyperparameters unchanged from the 16-bit baseline training sessions. Our training experiments include large, up to 175B parameter, language models. We also examine FP8 post-training-quantization of language models trained using 16-bit formats that resisted fixed point int8 quantization.
Hadamard single-pixel imaging (HSI) is an appealing imaging technique due to its features of low hardware complexity and industrial cost. To improve imaging efficiency, many studies have focused on sorting Hadamard patterns to obtain reliable reconstructed images with very few samples. In this study, we present an efficient HSI imaging method that employs an exponential probability function to sample Hadamard spectra along a direction with better energy concentration for obtaining Hadamard patterns. We also propose an XY order to further optimize the pattern-selection method with extremely fast Hadamard order generation while retaining the original performance. We used the compressed sensing algorithm for image reconstruction. The simulation and experimental results show that these pattern-selection method reliably reconstructs objects and preserves the edge and details of images.
Target-oriented Opinion Words Extraction (TOWE) is a fine-grained sentiment analysis task that aims to extract the corresponding opinion words of a given opinion target from the sentence. Recently, deep learning approaches have made remarkable progress on this task. Nevertheless, the TOWE task still suffers from the scarcity of training data due to the expensive data annotation process. Limited labeled data increase the risk of distribution shift between test data and training data. In this paper, we propose exploiting massive unlabeled data to reduce the risk by increasing the exposure of the model to varying distribution shifts. Specifically, we propose a novel Multi-Grained Consistency Regularization (MGCR) method to make use of unlabeled data and design two filters specifically for TOWE to filter noisy data at different granularity. Extensive experimental results on four TOWE benchmark datasets indicate the superiority of MGCR compared with current state-of-the-art methods. The in-depth analysis also demonstrates the effectiveness of the different-granularity filters. Our codes are available at https://github.com/TOWESSL/TOWESSL.
Image captioning models are usually trained according to human annotated ground-truth captions, which could generate accurate but generic captions. In this paper, we focus on generating the distinctive captions that can distinguish the target image from other similar images. To evaluate the distinctiveness of captions, we introduce a series of metrics that use large-scale vision-language pre-training model CLIP to quantify the distinctiveness. To further improve the distinctiveness of captioning models, we propose a simple and effective training strategy which trains the model by comparing target image with similar image group and optimizing the group embedding gap. Extensive experiments are conducted on various baseline models to demonstrate the wide applicability of our strategy and the consistency of metric results with human evaluation. By comparing the performance of our best model with existing state-of-the-art models, we claim that our model achieves new state-of-the-art towards distinctiveness objective.
A nonnegative latent factorization of tensors (NLFT) model can well model the temporal pattern hidden in nonnegative quality-of-service (QoS) data for predicting the unobserved ones with high accuracy. However, existing NLFT models' objective function is based on Euclidean distance, which is only a special case of \b{eta}-divergence. Hence, can we build a generalized NLFT model via adopting \b{eta}-divergence to achieve prediction accuracy gain? To tackle this issue, this paper proposes a \b{eta}-divergence-based NLFT model (\b{eta}-NLFT). Its ideas are two-fold 1) building a learning objective with \b{eta}-divergence to achieve higher prediction accuracy, and 2) implementing self-adaptation of hyper-parameters to improve practicability. Empirical studies on two dynamic QoS datasets demonstrate that compared with state-of-the-art models, the proposed \b{eta}-NLFT model achieves the higher prediction accuracy for unobserved QoS data.