Large Language Models (LLMs) pose a new paradigm of modeling and computation for information tasks. Recommendation systems are a critical application domain poised to benefit significantly from the sequence modeling capabilities and world knowledge inherent in these large models. In this paper, we introduce PLUM, a framework designed to adapt pre-trained LLMs for industry-scale recommendation tasks. PLUM consists of item tokenization using Semantic IDs, continued pre-training (CPT) on domain-specific data, and task-specific fine-tuning for recommendation objectives. For fine-tuning, we focus particularly on generative retrieval, where the model is directly trained to generate Semantic IDs of recommended items based on user context. We conduct comprehensive experiments on large-scale internal video recommendation datasets. Our results demonstrate that PLUM achieves substantial improvements for retrieval compared to a heavily-optimized production model built with large embedding tables. We also present a scaling study for the model's retrieval performance, our learnings about CPT, a few enhancements to Semantic IDs, along with an overview of the training and inference methods that enable launching this framework to billions of users in YouTube.

Tracking objects in three-dimensional space is critical for autonomous driving. To ensure safety while driving, the tracker must be able to reliably track objects across frames and accurately estimate their states such as velocity and acceleration in the present. Existing works frequently focus on the association task while either neglecting the model’s performance on state estimation or deploying complex heuristics to predict the states. In this paper, we propose STT, a Stateful Tracking model built with Transformers, that can consistently track objects in the scenes while also predicting their states accurately. STT consumes rich appearance, geometry, and motion signals through long term history of detections and is jointly optimized for both data association and state estimation tasks. Since the standard tracking metrics like MOTA and MOTP do not capture the combined performance of the two tasks in the wider spectrum of object states, we extend them with new metrics called S-MOTA and MOTPSthat address this limitation. STT achieves competitive real-time performance on the Waymo Open Dataset.

Accurate understanding and prediction of human behaviors are critical prerequisites for autonomous vehicles, especially in highly dynamic and interactive scenarios such as intersections in dense urban areas. In this work, we aim at identifying crossing pedestrians and predicting their future trajectories. To achieve these goals, we not only need the context information of road geometry and other traffic participants but also need fine-grained information of the human pose, motion and activity, which can be inferred from human keypoints. In this paper, we propose a novel multi-task learning framework for pedestrian crossing action recognition and trajectory pre-diction, which utilizes 3D human keypoints extracted from raw sensor data to capture rich information on human pose and activity. Moreover, we propose to apply two auxiliary tasks and contrastive learning to enable auxiliary supervisions to improve the learned keypoints representation, which further enhances the performance of major tasks. We validate our approach on a large-scale in-house dataset, as well as a public benchmark dataset, and show that our approach achieves state-of-the-art performance on a wide range of evaluation metrics. The effectiveness of each model component is validated in a detailed ablation study.

The quadrotor unmanned aerial vehicle (UAV) is widely used due to its low maintenance cost, high maneuverability and strong hovering capability. Modeling the quadrotor UAV maneuver and simulating its performance can effectively support airborne intelligent algorithms training such as mission planning and scheduling. Traditional quadrotor UAV maneuver modeling method construct high-order mathematical model based on physics analysis, which require significant expertise and difficult to generalize. In this paper, we analyze the quadrotor UAV maneuvering process and propose a cascaded quadrotor UAV maneuvering model generating framework based on deep neural network. Using long short-term memory (LSTM) network to model each part of the quadrotor UAV maneuvering process individually, and flexibly combine network of each part to obtain varying granularity models. A variable-dimensional particle swarm optimization (PSO) algorithm based on detour foraging strategy is proposed to simultaneously determine the LSTM network's hidden layers and neurons of each hidden layer. We validate the effectiveness of the maneuvering model generation framework and the improved PSO algorithm through comparative experiments.

Recent years have witnessed the rapid progress of generative adversarial networks (GANs). However, the success of the GAN models hinges on a large amount of training data. This work proposes a regularization approach for training robust GAN models on limited data. We theoretically show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data. Extensive experiments on several benchmark datasets demonstrate that the proposed regularization scheme 1) improves the generalization performance and stabilizes the learning dynamics of GAN models under limited training data, and 2) complements the recent data augmentation methods. These properties facilitate training GAN models to achieve state-of-theart performance when only limited training data of the ImageNet benchmark is available. The source code is available at https://github.com/google/lecam-gan.

n recent years, text-guided image manipulation has gained increasing attention in the multimedia and computer vision community. The input to conditional image generation has evolved from image-only to multimodality. In this paper, we study a setting that allows users to edit an image with multiple objects using complex text instructions to add, remove, or change the objects. The inputs of the task are multimodal including (1) a reference image and (2) an instruction in natural language that describes desired modifications to the image. We propose a GAN-based method to tackle this problem. The key idea is to treat text as neural operators to locally modify the image feature. We show that the proposed model performs favorably against recent strong baselines on three public datasets. Specifically, it generates images of greater fidelity and semantic relevance, and when used as a image query, leads to better retrieval performance.

Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting. This paper makes three contributions. First, we establish the first benchmark of controlled real-world label noise from the web. This new benchmark enables us to study the web label noise in a controlled setting for the first time. The second contribution is a simple but effective method to overcome both synthetic and real noisy labels. We show that our method achieves the best result on our dataset as well as on two public benchmarks (CIFAR and WebVision). Third, we conduct the largest study by far into understanding deep neural networks trained on noisy labels across different noise levels, noise types, network architectures, and training settings.

We conduct image classification by learning a class-to-image distance function that matches objects. The set of objects in training images for an image class are treated as a collage. When presented with a test image, the best matching between this collage of training image objects and those in the test image is found. We validate the efficacy of the proposed model on the PASCAL 07 and SUN 09 datasets, showing that our model is effective for object classification and scene classification tasks. State-of-the-art image classification results are obtained, and qualitative results demonstrate that objects can be accurately matched.

Latent SVMs (LSVMs) are a class of powerful tools that have been successfully applied to many applications in computer vision. However, a limitation of LSVMs is that they rely on linear models. For many computer vision tasks, linear models are suboptimal and nonlinear models learned with kernels typically perform much better. Therefore it is desirable to develop the kernel version of LSVM. In this paper, we propose kernel latent SVM (KLSVM) -- a new learning framework that combines latent SVMs and kernel methods. We develop an iterative training algorithm to learn the model parameters. We demonstrate the effectiveness of KLSVM using three different applications in visual recognition. Our KLSVM formulation is very general and can be applied to solve a wide range of applications in computer vision and machine learning.

In this paper, we go beyond recognizing the actions of individuals and focus on group activities. This is motivated from the observation that human actions are rarely performed in isolation; the contextual information of what other people in the scene are doing provides a useful cue for understanding high-level activities. We propose a novel framework for recognizing group activities which jointly captures the group activity, the individual person actions, and the interactions among them. Two types of contextual information, group-person interaction and person-person interaction, are explored in a latent variable framework. In particular, we propose three different approaches to model the person-person interaction. One approach is to explore the structures of person-person interaction. Differently from most of the previous latent structured models, which assume a predefined structure for the hidden layer, e.g., a tree structure, we treat the structure of the hidden layer as a latent variable and implicitly infer it during learning and inference. The second approach explores person-person interaction in the feature level. We introduce a new feature representation called the action context (AC) descriptor. The AC descriptor encodes information about not only the action of an individual person in the video, but also the behavior of other people nearby. The third approach combines the above two. Our experimental results demonstrate the benefit of using contextual information for disambiguating group activities.

In this thesis, we present work towards addressing a grand challenge of computer vision, human action recognition and detection. In particular, we focus on the problem of recognizing and detecting the actions of a person from a video sequence. To recognize human actions in a video, a typical approach involves first detecting and tracking people, followed by classification. However, accurate tracking is challenging, and the state-of-art tracking methods are not reliable. Since accurate tracking is not a direct end-goal of action recognition, we consider tracking as a latent variable and train a model focused on action recognition. We propose a novel learning algorithm for training models with latent variables in a boosting framework. Moreover, we show that the algorithm can be used to train an action recognition model in which the tracking trajectory of a person is a latent variable. This new model outperforms baselines on a variety of datasets.

We consider the problem of content-based automated tag learning. In particular, we address semantic variations (sub-tags) of the tag. Each video in the training set is assumed to be associated with a sub-tag label, and we treat this sub-tag label as latent information. A latent learning framework based on LogitBoost is proposed, which jointly considers both the tag label and the latent sub-tag label. The latent sub-tag information is exploited in our framework to assist the learning of our end goal, i.e., tag prediction. We use the cowatch information to initialize the learning process. In experiments, we show that the proposed method achieves significantly better results over baselines on a large-scale testing video set which contains about 50 million YouTube videos.

We consider the problem of recognizing human actions from still images. We propose a novel approach that treats the pose of the person in the image as latent variables that will help with recognition. Different from other work that learns separate systems for pose estimation and action recognition, then combines them in an ad-hoc fashion, our system is trained in an integrated fashion that jointly considers poses and actions. Our learning objective is designed to directly exploit the pose information for action recognition. Our experimental results demonstrate that by inferring the latent poses, we can improve the final action recognition results.

We propose a discriminative model for recognizing group activities. Our model jointly captures the group activity, the individual person actions, and the interactions among them. Two new types of contextual information, group-person interaction and person-person interaction, are explored in a latent variable framework. Different from most of the previous latent structured models which assume a predefined structure for the hidden layer, e.g. a tree structure, we treat the structure of the hidden layer as a latent variable and implicitly infer it during learning and inference. Our experimental results demonstrate that by inferring this contextual information together with adaptive structures, the proposed model can significantly improve activity recognition performance.

In recent years, 3D face recognition has obtained much attention. Using 2D face image as probe and 3D face data as gallery is an alternative method to deal with computation complexity, expensive equipment and fussy pretreatment in 3D face recognition systems. In this paper we propose a learning based 2D-3D face matching method using the CCA to learn the mapping between 2D face image and 3D face data. This method makes it possible to match the on-site 2D face image with enrolled 3D face data. Our 2D-3D face matching method decreased the computation complexity drastically compared to the conventional 3D-3D face matching while keeping relative high recognition rate. Furthermore, to simplify the mapping between 2D face image and 3D face data, a patch based strategy is proposed to boost the accuracy of matching. And the kernel method is also evaluated to reveal the non-linear relationship. The experiment results show that CCA based method has good performance and patch based method has significant improvement compared to the holistic method.