最近在视觉跟踪中成功的关键因素之一是专用基准的可用性。尽管对跟踪研究有很大的受益，但现有的基准并没有与以前相同的难度，而最近的跟踪器的性能则主要是由于（i）引入了更复杂的基于变形金刚的方法，并且（ii）缺乏各种情况，因此缺乏各种情况。不良的可见性，例如恶劣的天气条件，伪装和成像效应。我们介绍了Avist，这是一个专门的基准，用于在具有不良可见性的不同情况下进行视觉跟踪。 Avist包括120个具有80k注释框架的具有挑战性的序列，涵盖了18种不同的方案，这些场景大致分为五个具有42个对象类别的属性。远景的主要贡献是涵盖恶劣天气条件的多样化和挑战性的情况，例如浓雾，大雨和沙尘暴；阻塞效应，包括火，阳光和溅水；不利成像效应，例如，低光；目标效应，包括小目标和干扰物对象以及伪装。我们进一步基准了17个关于Avist的流行和最新跟踪器，对它们跨属性的跟踪性能进行了详细分析，这表明了性能改善的巨大空间。我们认为，远景可以通过补充现有的基准，开发新的创意跟踪解决方案，以继续推动最先进的界限，从而极大地使跟踪社区受益。我们的数据集以及完整的跟踪性能评估可在以下网址提供：https：//github.com/visionml/pytracking

Recent work has shown the benefits of synthetic data for use in computer vision, with applications ranging from autonomous driving to face landmark detection and reconstruction. There are a number of benefits of using synthetic data from privacy preservation and bias elimination to quality and feasibility of annotation. Generating human-centered synthetic data is a particular challenge in terms of realism and domain-gap, though recent work has shown that effective machine learning models can be trained using synthetic face data alone. We show that this can be extended to include the full body by building on the pipeline of Wood et al. to generate synthetic images of humans in their entirety, with ground-truth annotations for computer vision applications. In this report we describe how we construct a parametric model of the face and body, including articulated hands; our rendering pipeline to generate realistic images of humans based on this body model; an approach for training DNNs to regress a dense set of landmarks covering the entire body; and a method for fitting our body model to dense landmarks predicted from multiple views.

To generate high quality rendering images for real time applications, it is often to trace only a few samples-per-pixel (spp) at a lower resolution and then supersample to the high resolution. Based on the observation that the rendered pixels at a low resolution are typically highly aliased, we present a novel method for neural supersampling based on ray tracing 1/4-spp samples at the high resolution. Our key insight is that the ray-traced samples at the target resolution are accurate and reliable, which makes the supersampling an interpolation problem. We present a mask-reinforced neural network to reconstruct and interpolate high-quality image sequences. First, a novel temporal accumulation network is introduced to compute the correlation between current and previous features to significantly improve their temporal stability. Then a reconstruct network based on a multi-scale U-Net with skip connections is adopted for reconstruction and generation of the desired high-resolution image. Experimental results and comparisons have shown that our proposed method can generate higher quality results of supersampling, without increasing the total number of ray-tracing samples, over current state-of-the-art methods.

In this paper we explore the task of modeling (semi) structured object sequences; in particular we focus our attention on the problem of developing a structure-aware input representation for such sequences. In such sequences, we assume that each structured object is represented by a set of key-value pairs which encode the attributes of the structured object. Given a universe of keys, a sequence of structured objects can then be viewed as an evolution of the values for each key, over time. We encode and construct a sequential representation using the values for a particular key (Temporal Value Modeling - TVM) and then self-attend over the set of key-conditioned value sequences to a create a representation of the structured object sequence (Key Aggregation - KA). We pre-train and fine-tune the two components independently and present an innovative training schedule that interleaves the training of both modules with shared attention heads. We find that this iterative two part-training results in better performance than a unified network with hierarchical encoding as well as over, other methods that use a {\em record-view} representation of the sequence \cite{de2021transformers4rec} or a simple {\em flattened} representation of the sequence. We conduct experiments using real-world data to demonstrate the advantage of interleaving TVM-KA on multiple tasks and detailed ablation studies motivating our modeling choices. We find that our approach performs better than flattening sequence objects and also allows us to operate on significantly larger sequences than existing methods.

In this chapter, we review and discuss the transformation of AI technology in HCI/UX work and assess how AI technology will change how we do the work. We first discuss how AI can be used to enhance the result of user research and design evaluation. We then discuss how AI technology can be used to enhance HCI/UX design. Finally, we discuss how AI-enabled capabilities can improve UX when users interact with computing systems, applications, and services.

Deep neural networks (DNNs) are vulnerable to a class of attacks called "backdoor attacks", which create an association between a backdoor trigger and a target label the attacker is interested in exploiting. A backdoored DNN performs well on clean test images, yet persistently predicts an attacker-defined label for any sample in the presence of the backdoor trigger. Although backdoor attacks have been extensively studied in the image domain, there are very few works that explore such attacks in the video domain, and they tend to conclude that image backdoor attacks are less effective in the video domain. In this work, we revisit the traditional backdoor threat model and incorporate additional video-related aspects to that model. We show that poisoned-label image backdoor attacks could be extended temporally in two ways, statically and dynamically, leading to highly effective attacks in the video domain. In addition, we explore natural video backdoors to highlight the seriousness of this vulnerability in the video domain. And, for the first time, we study multi-modal (audiovisual) backdoor attacks against video action recognition models, where we show that attacking a single modality is enough for achieving a high attack success rate.

Modern deep neural networks have achieved superhuman performance in tasks from image classification to game play. Surprisingly, these various complex systems with massive amounts of parameters exhibit the same remarkable structural properties in their last-layer features and classifiers across canonical datasets. This phenomenon is known as "Neural Collapse," and it was discovered empirically by Papyan et al. \cite{Papyan20}. Recent papers have theoretically shown the global solutions to the training network problem under a simplified "unconstrained feature model" exhibiting this phenomenon. We take a step further and prove the Neural Collapse occurrence for deep linear network for the popular mean squared error (MSE) and cross entropy (CE) loss. Furthermore, we extend our research to imbalanced data for MSE loss and present the first geometric analysis for Neural Collapse under this setting.

We present Second Thought, a new learning paradigm that enables language models (LMs) to re-align with human values. By modeling the chain-of-edits between value-unaligned and value-aligned text, with LM fine-tuning and additional refinement through reinforcement learning, Second Thought not only achieves superior performance in three value alignment benchmark datasets but also shows strong human-value transfer learning ability in few-shot scenarios. The generated editing steps also offer better interpretability and ease for interactive error correction. Extensive human evaluations further confirm its effectiveness.

In this paper, we investigate the possibility of the backward-differential-flow-like algorithm which starts from the minimum of convexification version of the polynomial. We apply the heat evolution convexification approach through Gaussian filtering, which is actually an accumulation version of Steklov's regularization. We generalize the fingerprint theory which was proposed in the theory of computer vision by A.L. Yuille and T. Poggio in 1980s, in particular their fingerprint trajectory equation, to characterize the evolution of minimizers across the scale. On the other hand, we propose the "seesaw" polynomials $p(x|s)$ and we find a seesaw differential equation $\frac{\partial p(x|s)}{\,ds}=-\frac{1}{p''(x)}$ to characterize the evolution of global minimizer $x^*(s)$ of $p(x|s)$ while varying $s$. Essentially, both the fingerprints $\mathcal{FP}_2$ and $\mathcal{FP}_3$ of $p(x)$, consisting of the zeros of $\frac{\partial^2 p(x,t)}{\partial x^2}$ and $\frac{\partial^3 p(x,t)}{\partial x^3}$, respectively, are independent of seesaw coefficient $s$, upon which we define the Confinement Zone and Escape Zone. Meanwhile, varying $s$ will monotonically condition the location of global minimizer of $p(x|s)$, and all these location form the Attainable Zone. Based on these concepts, we prove that the global minimizer $x^*$ of $p(x)$ can be inversely evolved from the global minimizer of its convexification polynomial $p(x,t_0)$ if and only if $x^*$ is included in the Escape Zone. In particular, we give detailed analysis for quartic and six degree polynomials.

The ''Propose-Test-Release'' (PTR) framework is a classic recipe for designing differentially private (DP) algorithms that are data-adaptive, i.e. those that add less noise when the input dataset is nice. We extend PTR to a more general setting by privately testing data-dependent privacy losses rather than local sensitivity, hence making it applicable beyond the standard noise-adding mechanisms, e.g. to queries with unbounded or undefined sensitivity. We demonstrate the versatility of generalized PTR using private linear regression as a case study. Additionally, we apply our algorithm to solve an open problem from ''Private Aggregation of Teacher Ensembles (PATE)'' -- privately releasing the entire model with a delicate data-dependent analysis.