An image is worth a thousand words, conveying information that goes beyond the mere visual content therein. In this paper, we study the intent behind social media images with an aim to analyze how visual information can facilitate recognition of human intent. Towards this goal, we introduce an intent dataset, Intentonomy, comprising 14K images covering a wide range of everyday scenes. These images are manually annotated with 28 intent categories derived from a social psychology taxonomy. We then systematically study whether, and to what extent, commonly used visual information, i.e., object and context, contribute to human motive understanding. Based on our findings, we conduct further study to quantify the effect of attending to object and context classes as well as textual information in the form of hashtags when training an intent classifier. Our results quantitatively and qualitatively shed light on how visual and textual information can produce observable effects when predicting intent.1

Visual engagement in social media platforms comprises interactions with photo posts including comments, shares, and likes. In this paper, we leverage such Visual Engagement clues as supervisory signals for representation learning. However, learning from engagement signals is non-trivial as it is not clear how to bridge the gap between low-level visual information and high-level social interactions. We present VisE, a weakly supervised learning approach, which maps social images to pseudo labels derived by clustered engagement signals. We then study how models trained in this way benefit subjective downstream computer vision tasks such as emotion recognition or political bias detection. Through extensive studies, we empirically demonstrate the effectiveness of VisE across a diverse set of classification tasks beyond the scope of conventional recognition1.

We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires monocular endoscopic videos and a multi-view stereo method, e.g., structure from motion, to supervise learning in a sparse manner. Consequently, our method requires neither manual labeling nor patient computed tomography (CT) scan in the training and application phases. In a cross-patient experiment using CT scans as groundtruth, the proposed method achieved submillimeter mean residual error. In a comparison study to recent self-supervised depth estimation methods designed for natural video on in vivo sinus endoscopy data, we demonstrate that the proposed approach outperforms the previous methods by a large margin. The source code for this work is publicly available online at https://github.com/lppllppl920/EndoscopyDepthEstimation-Pytorch.

When capturing videos on a mobile platform, often the target of interest is contaminated by the surrounding environment. To alleviate the visual irrelevance, camera panning and zooming provide the means to isolate a desired field of view (FOV). However, the captured audio is still contaminated by signals outside the FOV. This effect is unnatural---for human perception, visual and auditory cues must go hand-in-hand. We present the concept ofAudiovisual Zooming, whereby an auditory FOV is formed to match the visual. Our framework is built around the classic idea of beamforming, a computational approach to enhancing sound from a single direction using a microphone array. Yet, beamforming on its own can not incorporate the auditory FOV, as the FOV may include an arbitrary number of directional sources. We formulate our audiovisual zooming as a generalized eigenvalue problem and propose an algorithm for efficient computation on mobile platforms. To inform the algorithmic and physical implementation, we offer a theoretical analysis of our algorithmic components as well as numerical studies for understanding various design choices of microphone arrays. Finally, we demonstrate audiovisual zooming on two different mobile platforms: a mobile smartphone and a 360$^\circ $ spherical imaging system for video conference settings.

Deep learning methods are capable of performing sophisticated tasks when applied to a myriad of artificial intelligent (AI) research fields. In this paper, we introduce a novel approach to replace the inherently flawed beamforming step during ultrasound image formation by applying deep learning directly to RF channel data. Specifically, we pose the ultrasound beamforming process as a segmentation problem and apply a fully convolutional neural network architecture to segment anechoic cysts from surrounding tissue. We train our network on a dataset created using the Field II ultrasound simulation software to simulate plane wave imaging with a single insonification angle. We demonstrate the success of our architecture in extracting tissue information directly from the raw channel data, which completely bypasses the beamforming step that would otherwise require multiple insonification angles for plane wave imaging. Our simulated results produce mean Dice coefficient of 0.98 ± 0.02, when measuring the overlap between ground truth cyst locations and cyst locations determined by the network. The proposed approach is promising for developing dedicated deep-learning networks to improve the real-time ultrasound image formation process.

Action quality assessment is crucial in areas of sports, surgery and assembly line where action skills can be evaluated. In this paper, we propose the Segment-based P3D-fused network S3D built-upon ED-TCN and push the performance on the UNLV-Dive dataset by a significant margin. We verify that segment-aware training performs better than full-video training which turns out to focus on the water spray. We show that temporal segmentation can be embedded with few efforts.

Interventional applications of photoacoustic imaging typically require visualization of point-like targets, such as the small, circular, cross-sectional tips of needles, catheters, or brachytherapy seeds. When these point-like targets are imaged in the presence of highly echogenic structures, the resulting photoacoustic wave creates a reflection artifact that may appear as a true signal. We propose to use deep learning techniques to identify these types of noise artifacts for removal in experimental photoacoustic data. To achieve this goal, a convolutional neural network (CNN) was first trained to locate and classify sources and artifacts in pre-beamformed data simulated with -Wave. Simulations initially contained one source and one artifact with various medium sound speeds and 2-D target locations. Based on 3,468 test images, we achieved a 100% success rate in classifying both sources and artifacts. After adding noise to assess potential performance in more realistic imaging environments, we achieved at least 98% success rates for channel signal-to-noise ratios (SNRs) of -9dB or greater, with a severe decrease in performance below -21dB channel SNR. We then explored training with multiple sources and two types of acoustic receivers and achieved similar success with detecting point sources. Networks trained with simulated data were then transferred to experimental waterbath and phantom data with 100% and 96.67% source classification accuracy, respectively (particularly when networks were tested at depths that were included during training). The corresponding mean ± one standard deviation of the point source location error was 0.40 ± 0.22 mm and 0.38 ± 0.25 mm for waterbath and phantom experimental data, respectively, which provides some indication of the resolution limits of our new CNN-based imaging system. We finally show that the CNN-based information can be displayed in a novel artifact-free image format, enabling us to effectively remove reflection artifacts from photoacoustic images, which is not possible with traditional geometry-based beamforming.

Functional endoscopic sinus surgery (FESS) is one of the most common outpatient surgical procedures performed in the head and neck region. It is used to treat chronic sinusitis, a disease characterized by inflammation in the nose and surrounding paranasal sinuses, affecting about 15% of the adult population. During FESS, the nasal cavity is visualized using an endoscope, and instruments are used to remove tissues that are often within a millimeter of critical anatomical structures, such as the optic nerve, carotid arteries, and nasolacrimal ducts. To maintain orientation and to minimize the risk of damage to these structures, surgeons use surgical navigation systems to visualize the 3-D position of their tools on patients' preoperative Computed Tomographies (CTs). This paper presents an image-based method for enhanced endoscopic navigation. The main contributions are: (1) a system that enables a surgeon to asynchronously register a sequence of endoscopic images to a CT scan with higher accuracy than other reported solutions using no additional hardware; (2) the ability to report the robustness of the registration; and (3) evaluation on in vivo human data. The system also enables the overlay of anatomical structures, visible, or occluded, on top of video images. The methods are validated on four different data sets using multiple evaluation metrics. First, for experiments on synthetic data, we observe a mean absolute position error of 0.21mm and a mean absolute orientation error of 2.8° compared with ground truth. Second, for phantom data, we observe a mean absolute position error of 0.97mm and a mean absolute orientation error of 3.6° compared with the same motion tracked by an electromagnetic tracker. Third, for cadaver data, we use fiducial landmarks and observe an average reprojection distance error of 0.82mm. Finally, for in vivo clinical data, we report an average ICP residual error of 0.88mm in areas that are not composed of erectile tissue and an average ICP residual error of 1.09mm in areas that are composed of erectile tissue.

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal features from video frames and then feeding them into a temporal classifier that captures high-level temporal patterns. We describe a class of temporal models, which we call Temporal Convolutional Networks (TCNs), that use a hierarchy of temporal convolutions to perform fine-grained action segmentation or detection. Our Encoder-Decoder TCN uses pooling and upsampling to efficiently capture long-range temporal patterns whereas our Dilated TCN uses dilated convolutions. We show that TCNs are capable of capturing action compositions, segment durations, and long-range dependencies, and are over a magnitude faster to train than competing LSTM-based Recurrent Neural Networks. We apply these models to three challenging fine-grained datasets and show large improvements over the state of the art.

Limited labeled data are available for the research of estimating facial expression intensities. For instance, the ability to train deep networks for automated pain assessment is limited by small datasets with labels of patient-reported pain intensities. Fortunately, fine-tuning from a data-extensive pre-trained domain, such as face verification, can alleviate this problem. In this paper, we propose a network that fine-tunes a state-of-the-art face verification network using a regularized regression loss and additional data with expression labels. In this way, the expression intensity regression task can benefit from the rich feature representations trained on a huge amount of data for face verification. The proposed regularized deep regressor is applied to estimate the pain expression intensity and verified on the widely-used UNBC-McMaster Shoulder-Pain dataset, achieving the state-of-the-art performance. A weighted evaluation metric is also proposed to address the imbalance issue of different pain intensities.

Functional endoscopic sinus surgery (FESS) is a surgical procedure used to treat acute cases of sinusitis and other sinus diseases. FESS is fast becoming the preferred choice of treatment due to its minimally invasive nature. However, due to the limited field of view of the endoscope, surgeons rely on navigation systems to guide them within the nasal cavity. State of the art navigation systems report registration accuracy of over 1mm, which is large compared to the size of the nasal airways. We present an anatomically constrained video-CT registration algorithm that incorporates multiple video features. Our algorithm is robust in the presence of outliers. We also test our algorithm on simulated and in-vivo data, and test its accuracy against degrading initializations. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Object recognition systems have shown great progress over recent years. However, creating object representations that are robust to changes in viewpoint while capturing local visual details continues to be a challenge. In particular, recent convolutional architectures employ spatial pooling to achieve scale and shift invariances, but they are still sensitive to out-of-plane rotations. In this paper, we formulate a probabilistic framework for analyzing the performance of pooling. This framework suggests two directions for improvement. First, we apply multiple scales of filters coupled with different pooling granularities, and second we make use of color as an additional pooling domain, thereby reducing the sensitivity to spatial deformations. We evaluate our algorithm on the object instance recognition task using two independent publicly available RGB-D datasets, and demonstrate significant improvements over the current state-of-the-art. In addition, we present a new dataset for industrial objects to further validate the effectiveness of our approach versus other state-of-the-art approaches for object recognition using RGB-D data.

Surgeons perform minimally invasive surgery using an image delivered by a laparoscope and a camera system that provides a high definition 2D image, but this leaves the surgeon without 3D depth perception. The lack of depth perception can slow the surgeon, increase the risk of misidentifying structures, and/or inadvertently cause unwanted injury to tissues surrounding the surgical site. To address the lack of depth perception, we propose a Surgical Structured Light (SSL) system that includes a 3D sensor capable of measuring and modeling the surgical site during a procedure. The 3D information provided by this system can enable the surgeon to: 1) improve the navigation of tools based on precise localization of instruments in relation to structures in the surgical site, 2) allow 3D visualizations side-by-side with a standard 2D color image, and 3) precisely measure sizes of structures (e.g., tumors) and distances between structures with simple mouse clicks. We demonstrate the accuracy of our SSL system using ex-vivo data on both a cylinder calibration object as well as various plastic organs.

Continuum robots offer significant advantages for surgical intervention due to their down-scalability, dexterity, and structural flexibility. While structural compliance offers a passive way to guard against trauma, it necessitates robust methods for online estimation of the robot configuration in order to enable precise position and manipulation control. In this paper, we address the pose estimation problem by applying a novel mapping of the robot configuration to a feature descriptor space using stereo vision. We generate a mapping of known features through a supervised learning algorithm that relates the feature descriptor to known ground truth. Features are represented in a reduced sub-space, which we call eigen-features. The descriptor provides some robustness to occlusions, which are inherent to surgical environments, and the methodology that we describe can be applied to multi-segment continuum robots for closed-loop control. Experimental validation on a single-segment continuum robot demonstrates the robustness and efficacy of the algorithm for configuration estimation. Results show that the errors are in the range of 1°.

In this paper we present an online algorithm for robustly tracking surgical tools in dynamic environments that can assist a surgeon during in-vivo robotic surgery procedures. The next generation of in-vivo robotic surgical devices includes integrated imaging and effector platforms that need to be controlled through real-time visual feedback. Our tracking algorithm learns the appearance of the tool online to account for appearance and perspective changes. In addition, the tracker uses multiple features working together to model the object and discover new areas of the tool as it moves quickly, exits and re-enters the scene, or becomes occluded and requires recovery. The algorithm can persist through changes in lighting and pose by using a memory database, which is built online, using a series of features working together to exploit different aspects of the object being tracked. We present results using real in-vivo imaging data from a human partial nephrectomy.