Designing 3D scenes is traditionally a challenging and laborious task that demands both artistic expertise and proficiency with complex software. Recent advances in text-to-3D generation have greatly simplified this process by letting users create scenes based on simple text descriptions. However, as these methods generally require extra training or in-context learning, their performance is often hindered by the limited availability of high-quality 3D data. In contrast, modern text-to-image models learned from web-scale images can generate scenes with diverse, reliable spatial layouts and consistent, visually appealing styles. Our key insight is that instead of learning directly from 3D scenes, we can leverage generated 2D images as an intermediary to guide 3D synthesis. In light of this, we introduce ArtiScene, a training-free automated pipeline for scene design that integrates the flexibility of free-form text-to-image generation with the diversity and reliability of 2D intermediary layouts. First, we generate 2D images from a scene description, then extract the shape and appearance of objects to create 3D models. These models are assembled into the final scene using geometry, position, and pose information derived from the same intermediary image. Being generalizable to a wide range of scenes and styles, ArtiScene outperforms state-of-the-art benchmarks by a large margin in layout and aesthetic quality by quantitative metrics. It also averages a 74.89 % winning rate in extensive user studies and 95.07 % in GPT-4o evaluation.

Generating detailed and accurate descriptions for specific regions in images and videos remains a fundamental challenge for vision-language models. We introduce the Describe Anything Model (DAM), a model designed for detailed localized captioning (DLC). DAM preserves both local details and global context through two key innovations: a focal prompt, which ensures high-resolution encoding of targeted regions, and a localized vision backbone, which integrates precise localization with its broader context. To tackle the scarcity of high-quality DLC data, we propose a Semi-supervised learning (SSL)-based Data Pipeline (DLC-SDP). DLC-SDP starts with existing segmentation datasets and expands to unlabeled web images using SSL. We introduce DLC-Bench, a benchmark designed to evaluate DLC without relying on reference captions. DAM sets new state-of-the-art on 7 benchmarks spanning keyword-level, phrase-level, and detailed multi-sentence localized image and video captioning.

Recently, data-driven inertial navigation approaches have demonstrated their capability of using well-trained neural networks to obtain accurate position estimates from inertial measurement units (IMUs) measurements. In this paper, we propose a novel robust Contextual Transformer-based network for Inertial Navigation (CTIN) to accurately predict velocity and trajectory. To this end, we first design a ResNet-based encoder enhanced by local and global multi-head self-attention to capture spatial contextual information from IMU measurements. Then we fuse these spatial representations with temporal knowledge by leveraging multi-head attention in the Transformer decoder. Finally, multi-task learning with uncertainty reduction is leveraged to improve learning efficiency and prediction accuracy of velocity and trajectory. Through extensive experiments over a wide range of inertial datasets (e.g., RIDI, OxIOD, RoNIN, IDOL, and our own), CTIN is very robust and outperforms state-of-the-art models.

We propose ACProp (Asynchronous-centering-Prop), an adaptive optimizer which combines centering of second momentum and asynchronous update (e.g. for $t$-th update, denominator uses information up to step $t-1$, while numerator uses gradient at $t$-th step). ACProp has both strong theoretical properties and empirical performance. With the example by Reddi et al. (2018), we show that asynchronous optimizers (e.g. AdaShift, ACProp) have weaker convergence condition than synchronous optimizers (e.g. Adam, RMSProp, AdaBelief); within asynchronous optimizers, we show that centering of second momentum further weakens the convergence condition. We demonstrate that ACProp has a convergence rate of $O(\frac{1}{\sqrt{T}})$ for the stochastic non-convex case, which matches the oracle rate and outperforms the $O(\frac{logT}{\sqrt{T}})$ rate of RMSProp and Adam. We validate ACProp in extensive empirical studies: ACProp outperforms both SGD and other adaptive optimizers in image classification with CNN, and outperforms well-tuned adaptive optimizers in the training of various GAN models, reinforcement learning and transformers. To sum up, ACProp has good theoretical properties including weak convergence condition and optimal convergence rate, and strong empirical performance including good generalization like SGD and training stability like Adam. We provide the implementation at \url{ https://github.com/juntang-zhuang/ACProp-Optimizer}.

Transfer learning has become the de facto practice to reuse a deep neural network (DNN) that is pre-trained with abundant training data in a source task to improve the model training on target tasks with smaller-scale training data. In this paper, we first investigate the correlation between the DNN's pre-training performance in the source task and their transfer results in the downstream tasks. We find that high performance of a pre-trained model does not necessarily imply high transferability. We then propose a metric, named Fréchet Pre-train Distance, to estimate the transferability of a deep neural network. By applying the proposed Fréchet Pre-train Distance, we are able to identify the optimal pre-trained checkpoint, and then achieve high transferability on downstream tasks. Finally, we investigate several factors impacting DNN's transferability including normalization, different networks and learning rates. The results consistently support our conclusions.

Speaker diarization, which is to find the speech segments of specific speakers, has been widely used in human-centered applications such as video conferences or human-computer interaction systems. In this paper, we propose a self-supervised audio-video synchronization learning method to address the problem of speaker diarization without massive labeling effort. We improve the previous approaches by introducing two new loss functions: the dynamic triplet loss and the multinomial loss. We test them on a real-world human-computer interaction system and the results show our best model yields a remarkable gain of +8% F1-scores as well as diarization error rate reduction. Finally, we introduce a new large scale audio-video corpus designed to fill the vacancy of audio-video dataset in Chinese.

Most popular optimizers for deep learning can be broadly categorized as adaptive methods (e.g.~Adam) and accelerated schemes (e.g.~stochastic gradient descent (SGD) with momentum). For many models such as convolutional neural networks (CNNs), adaptive methods typically converge faster but generalize worse compared to SGD; for complex settings such as generative adversarial networks (GANs), adaptive methods are typically the default because of their stability. We propose AdaBelief to simultaneously achieve three goals: fast convergence as in adaptive methods, good generalization as in SGD, and training stability. The intuition for AdaBelief is to adapt the stepsize according to the "belief" in the current gradient direction. Viewing the exponential moving average (EMA) of the noisy gradient as the prediction of the gradient at the next time step, if the observed gradient greatly deviates from the prediction, we distrust the current observation and take a small step; if the observed gradient is close to the prediction, we trust it and take a large step. We validate AdaBelief in extensive experiments, showing that it outperforms other methods with fast convergence and high accuracy on image classification and language modeling. Specifically, on ImageNet, AdaBelief achieves comparable accuracy to SGD. Furthermore, in the training of a GAN on Cifar10, AdaBelief demonstrates high stability and improves the quality of generated samples compared to a well-tuned Adam optimizer.

The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dateset. On the contrary, it is fairly convenient, fast, and cheap to collect training images from the Web along with their noisy labels. This signifies the need of alternative approaches to training deep neural networks using such noisy labels. Existing methods tackling this problem either try to identify and correct the wrong labels or reweigh the data terms in the loss function according to the inferred noisy rates. Both strategies inevitably incur errors for some of the data points. In this paper, we contend that it is actually better to ignore the labels of some of the data points than to keep them if the labels are incorrect, especially when the noisy rate is high. After all, the wrong labels could mislead a neural network to a bad local optimum. We suggest a two-stage framework for the learning from noisy labels. In the first stage, we identify a small portion of images from the noisy training set of which the labels are correct with a high probability. The noisy labels of the other images are ignored. In the second stage, we train a deep neural network in a semi-supervised manner. This framework effectively takes advantage of the whole training set and yet only a portion of its labels that are most likely correct. Experiments on three datasets verify the effectiveness of our approach especially when the noisy rate is high.

The user's Quality of Experience (QoE) is an assessment of the human experience. It's not only influenced by Quality of Service (QoS) parameters but also influenced by user's preference for video content. This article studies user's preference for video content and how user's QoE changes on account of their biases. Through two experiments, it is concluded that the higher the user's preference score is, the higher the user rate MOS and the less MOS reduces when the resolution of video decrease. That is, the more user likes the video content, the more tolerant they will be to quality reduction of videos. Then a network resource management strategy is proposed based on the conclusion, and a web site platform is established for the test. Eventually we get the result that 87.0% of the participants have their MOS value increased after using the strategy.

In order to assess the quality of experience (QoE) of HTTP video streaming, the model of three levels of quality of service (QoS): network QoS, application QoS and QoE, is employed in this paper. We mainly study the effects of pause position, and therefore propose two new application performance metrics: location of each pause and time interval of pauses. We first focus on the buffer behaviors of the video player, and correlate the application QoS with the network QoS, based on the analytical model and mathematical model. Then the subjective tests and experiments are carried out to assess how application performance metrics affect the QoE, and the Back Propagation Neural Net (BPNN) is established to map the application QoS to the QoE. This paper reveals that the pauses in the front part of the video, as well as the shorter time interval of pauses, have a higher negative effect on QoE of HTTP video streaming.