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.

Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior performance when compared to LiDAR-based techniques. Through systematic analysis, we identified that per-object depth estimation accuracy is a major factor bounding the performance. Motivated by this observation, we propose a multi-level fusion method that combines different representations (RGB and pseudo-LiDAR) and temporal information across multiple frames for objects (tracklets) to enhance per-object depth estimation. Our proposed fusion method achieves the state-of-the-art performance of per-object depth estimation on the Waymo Open Dataset, the KITTI detection dataset, and the KITTI MOT dataset. We further demonstrate that by simply replacing estimated depth with fusion-enhanced depth, we can achieve significant improvements in monocular 3D perception tasks, including detection and tracking.

Recent advances in deep convolutional neural networks (CNNs) have motivated researchers to adapt CNNs to directly model points in 3D point clouds. Modeling local structure has been proven to be important for the success of convolutional architectures, and researchers exploited the modeling of local point sets in the feature extraction hierarchy. However, limited attention has been paid to explicitly model the geometric structure amongst points in a local region. To address this problem, we propose Geo-CNN, which applies a generic convolution-like operation dubbed as GeoConv to each point and its local neighborhood. Local geometric relationships among points are captured when extracting edge features between the center and its neighboring points. We first decompose the edge feature extraction process onto three orthogonal bases, and then aggregate the extracted features based on the angles between the edge vector and the bases. This encourages the network to preserve the geometric structure in Euclidean space throughout the feature extraction hierarchy. GeoConv is a generic and efficient operation that can be easily integrated into 3D point cloud analysis pipelines for multiple applications. We evaluate Geo-CNN on ModelNet40 and KITTI and achieve state-of-the-art performance.

We address scene layout modeling for recognizing agent-in-place actions, which are actions associated with agents who perform them and the places where they occur, in the context of outdoor home surveillance. We introduce a novel representation to model the geometry and topology of scene layouts so that a network can generalize from the layouts observed in the training scenes to unseen scenes in the test set. This Layout-Induced Video Representation (LIVR) abstracts away low-level appearance variance and encodes geometric and topological relationships of places to explicitly model scene layout. LIVR partitions the semantic features of a scene into different places to force the network to learn generic place-based feature descriptions which are independent of specific scene layouts; then, LIVR dynamically aggregates features based on connectivities of places in each specific scene to model its layout. We introduce a new Agent-in-Place Action (APA) dataset to show that our method allows neural network models to generalize significantly better to unseen scenes.

Unconstrained video-based face recognition is a challenging problem due to significant within-video variations caused by pose, occlusion and blur. To tackle this problem, an effective idea is to propagate the identity from high-quality faces to low-quality ones through contextual connections, which are constructed based on context such as body appearance. However, previous methods have often propagated erroneous information due to lack of uncertainty modeling of the noisy contextual connections. In this paper, we propose the Uncertainty-Gated Graph (UGG), which conducts graph-based identity propagation between tracklets, which are represented by nodes in a graph. UGG explicitly models the uncertainty of the contextual connections by adaptively updating the weights of the edge gates according to the identity distributions of the nodes during inference. UGG is a generic graphical model that can be applied at only inference time or with end-to-end training. We demonstrate the effectiveness of UGG with state-of-the-art results in the recently released challenging Cast Search in Movies and IARPA Janus Surveillance Video Benchmark dataset.

We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images. Detection progresses in a coarse-to-fine manner, first on a down-sampled version of the image and then on a sequence of higher resolution regions identified as likely to improve the detection accuracy. Built upon reinforcement learning, our approach consists of a model (R-net) that uses coarse detection results to predict the potential accuracy gain for analyzing a region at a higher resolution and another model (Q-net) that sequentially selects regions to zoom in. Experiments on the Caltech Pedestrians dataset show that our approach reduces the number of processed pixels by over 50% without a drop in detection accuracy. The merits of our approach become more significant on a high resolution test set collected from YFCC100M dataset, where our approach maintains high detection performance while reducing the number of processed pixels by about 70% and the detection time by over 50%.

We present an image-based VIirtual Try-On Network (VITON) without using 3D information in any form, which seamlessly transfers a desired clothing item onto the corresponding region of a person using a coarse-to-fine strategy. Conditioned upon a new clothing-agnostic yet descriptive person representation, our framework first generates a coarse synthesized image with the target clothing item overlaid on that same person in the same pose. We further enhance the initial blurry clothing area with a refinement network. The network is trained to learn how much detail to utilize from the target clothing item, and where to apply to the person in order to synthesize a photo-realistic image in which the target item deforms naturally with clear visual patterns. Experiments on our newly collected Zalando dataset demonstrate its promise in the image-based virtual try-on task over state-of-the-art generative models.

To reduce the significant redundancy in deep Convolutional Neural Networks (CNNs), most existing methods prune neurons by only considering the statistics of an individual layer or two consecutive layers (e.g., prune one layer to minimize the reconstruction error of the next layer), ignoring the effect of error propagation in deep networks. In contrast, we argue that for a pruned network to retain its predictive power, it is essential to prune neurons in the entire neuron network jointly based on a unified goal: minimizing the reconstruction error of important responses in the "final response layer" (FRL), which is the second-to-last layer before classification. Specifically, we apply feature ranking techniques to measure the importance of each neuron in the FRL, formulate network pruning as a binary integer optimization problem, and derive a closed-form solution to it for pruning neurons in earlier layers. Based on our theoretical analysis, we propose the Neuron Importance Score Propagation (NISP) algorithm to propagate the importance scores of final responses to every neuron in the network. The CNN is pruned by removing neurons with least importance, and it is then fine-tuned to recover its predictive power. NISP is evaluated on several datasets with multiple CNN models and demonstrated to achieve significant acceleration and compression with negligible accuracy loss.

This paper addresses the problem of detecting relevant motion caused by objects of interest (e.g., person and vehicles) in large scale home surveillance videos. The traditional method usually consists of two separate steps, i.e., detecting moving objects with background subtraction running on the camera, and filtering out nuisance motion events with deep learning based object detection and tracking running on cloud. The method is extremely slow, and does not fully leverage the spatial-temporal redundancies with a pre-trained off-the-shelf object detector. To dramatically speedup relevant motion event detection and improve its performance, we propose a novel network for relevant motion event detection, ReMotENet, which is a unified, end-to-end data-driven method using spatial-temporal attention-based 3D ConvNets to jointly model the appearance and motion of objects-of-interest in a video. Re-MotENet parses an entire video clip in one forward pass of a neural network to achieve significant speedup, which exploits the properties of home surveillance videos, and enhances 3D ConvNets with a spatial-temporal attention model and frame differencing to encourage the network to focus on the relevant moving objects. Experiments demonstrate that our method can achieve comparable or event better performance than the object detection based method but with three to four orders of magnitude speedup (up to 20k) on GPU devices. Our network is efficient, compact and light-weight. It can detect relevant motion on a 15s surveillance video clip within 4-8 milliseconds on a GPU and a fraction of second (0.17-0.39s) on a CPU with a model size of less than 1MB.

Spatial relationships between objects provide important information for text-based image retrieval. As users are more likely to describe a scene from a real world perspective, using 3D spatial relationships rather than 2D relationships that assume a particular viewing direction, one of the main challenges is to infer the 3D structure that bridges images with users text descriptions. However, direct inference of 3D structure from images requires learning from large scale annotated data. Since interactions between objects can be reduced to a limited set of atomic spatial relations in 3D, we study the possibility of inferring 3D structure from a text description rather than an image, applying physical relation models to synthesize holistic 3D abstract object layouts satisfying the spatial constraints present in a textual description. We present a generic framework for retrieving images from a textual description of a scene by matching images with these generated abstract object layouts. Images are ranked by matching object detection outputs (bounding boxes) to 2D layout candidates (also represented by bounding boxes) which are obtained by projecting the 3D scenes with sampled camera directions. We validate our approach using public indoor scene datasets and show that our method outperforms baselines built upon object occurrence histograms and learned 2D pairwise relations.

Understanding the visual relationship between two objects involves identifying the subject, the object, and a predicate relating them. We leverage the strong correlations between the predicate and the hsubj; obji pair (both semantically and spatially) to predict predicates conditioned on the subjects and the objects. Modeling the three entities jointly more accurately reflects their relationships compared to modeling them independently, but it complicates learning since the semantic space of visual relationships is huge and training data is limited, especially for longtail relationships that have few instances. To overcome this, we use knowledge of linguistic statistics to regularize visual model learning. We obtain linguistic knowledge by mining from both training annotations (internal knowledge) and publicly available text, e.g., Wikipedia (external knowledge), computing the conditional probability distribution of a predicate given a (subj, obj) pair. As we train the visual model, we distill this knowledge into the deep model to achieve better generalization. Our experimental results on the Visual Relationship Detection (VRD) and Visual Genome datasets suggest that with this linguistic knowledge distillation, our model outperforms the stateof- the-art methods significantly, especially when predicting unseen relationships (e.g., recall improved from 8.45% to 19.17% on VRD zero-shot testing set).

Modern brain mapping techniques are producing increasingly large datasets of anatomical or functional connection patterns. Recently, it became possible to record detailed live imaging videos of mammal brain while the subject is engaging routine activity. We analyze a dataset of videos recorded from ten mice to describe how to detect neurons, extract neuron signals, map correlation of neuron signals to mice activity, detect the network topology of active neurons, and analyze network topology characteristics. We propose neuron position alignment to compensate the distortion and movement of cerebral cortex in live mouse brain and the background luminance compensation to extract and model neuron activity. To find out the network topology as an undirected graph model, a cross-correlation based method is proposed and used for analysis. Afterwards, we did preliminary analysis on network topologies. The significance of this paper is on how to extract neuron activities from live mouse brain imaging videos and a network analysis method to analyze topology that can potentially provide insight on how neurons are actively connected under stimulus, rather than analyzing static neural networks.

We propose a personality detection algorithm based on human perceptions of images and created a mobile social application named Date gram to test the efficiency of our algorithm and connect people who share similar image perceptions. We detect user's Big Five personality based on their perceptual opinions on several images. Users in Date gram are matched to play visual-sentiment games, through which their connections based on personality similarity are further strengthened. Datagram utilizes techniques of image sentiment detection to analyze user's personality. Given the collected personal sentiment perception data, we proposed personality-mapping algorithm to categorize users into "Big Five" personality. After the Adjective-Noun-Pairs (ANPs) are extracted from each image, a personalized image-profile that consists of multiple pairs of ANPs and corresponding user decisions is generated. This profile is treated as the input of our algorithm, and a modified Latent Dirichlet Allocation (LDA) model is applied to extract personality-related features. "Big Five" personality values are calculated by a word-personality mapping algorithm where the technique of Linguistic Inquiry and Word Count (LIWC) is used. To evaluate our proposed algorithm, we did user studies over visual sentiments as well as personality detections. The results demonstrate that sentimental opinions from different persons vary significantly towards the same image, people would prefer to connect with those sharing similar perceptions of images and similar personalities with them.