Fuxin Li

Video Segmentation by Tracking Many Figure-Ground Segments

We propose an unsupervised video segmentation approach by simultaneously tracking multiple holistic figure-ground segments. Segment tracks are initialized from a pool of segment proposals generated from a figure-ground segmentation algorithm. Then, online non-local appearance models are trained incrementally for each track using a multi-output regularized least squares formulation. By using the same set of training examples for all segment tracks, a computational trick allows us to track hundreds of segment tracks efficiently, as well as perform optimal online updates in closed-form. Besides, a new composite statistical inference approach is proposed for refining the obtained segment tracks, which breaks down the initial segment proposals and recombines for better ones by utilizing high-order statistic estimates from the appearance model and enforcing temporal consistency. For evaluating the algorithm, a dataset, SegTrack v2, is collected with about 1,000 frames with pixel-level annotations. The proposed framework outperforms state-of-the-art approaches in the dataset, showing its efficiency and robustness to challenges in different video sequences.

Object recognition as ranking holistic figure-ground hypotheses

We present an approach to visual object-class recognition and segmentation based on a pipeline that combines multiple, holistic figure-ground hypotheses generated in a bottom-up, object independent process. Decisions are performed based on continuous estimates of the spatial overlap between image segment hypotheses and each putative class. We differ from existing approaches not only in our seemingly unreasonable assumption that good object-level segments can be obtained in a feed-forward fashion, but also in framing recognition as a regression problem. Instead of focusing on a one-vs-all winning margin that can scramble ordering inside the non-maximum (non-winning) set, learning produces a globally consistent ranking with close ties to segment quality, hence to the extent entire object or part hypotheses spatially overlap with the ground truth. We demonstrate results beyond the current state of the art for image classification, object detection and semantic segmentation, in a number of challenging datasets including Caltech-101, ETHZ-Shape and PASCAL VOC 2009.

Concanavalin A-captured Glycoproteins in Healthy Human Urine

Both the urinary proteome and its glycoproteome can reflect human health status, and more directly, functions of kidney and urinary tracts. Because the high abundance protein albumin is not N-glycosylated, the urine N-glycoprotein enrichment procedure could deplete it, and urine proteome could thus provide a more detailed protein profile in addition to glycosylation information especially when albuminuria occurs in some kidney diseases. In terms of describing the details of urinary proteins, the urine glycoproteome is even a better choice than the proteome itself. Pooled urine samples from healthy volunteers were collected and acetone-precipitated for proteins. N-Linked glycoproteins enriched with concanavalin A affinity purification were separated and analyzed by SDS-PAGE-reverse phase LC/MS/MS or two-dimensional LC/MS/MS. A total of 225 urinary proteins were identified based on two-hit criteria with reliability over 97% for each peptide. Among these proteins, 94 were identified in previous urine proteome works, 150 were annotated as glycoproteins in Swiss-Prot, and 43 were predicted as glycoproteins by NetNGlyc 1.0. A number of known biomarkers and disease-related glycoproteins were identified. Because changes in protein quantity or the glycosylation status can lead to changes in the concanavalin A-captured glycoprotein profile, specific urine glycoproteome patterns might be observed for specific pathological conditions as multiplex urinary biomarkers. Knowledge of the urine glycoproteome is important in understanding kidney and body function.

Joint Semantic Segmentation and 3D Reconstruction from Monocular Video

We present an approach for joint inference of 3D scene structure and semantic labeling for monocular video. Starting with monocular image stream, our framework produces a 3D volumetric semantic + occupancy map, which is much more useful than a series of 2D semantic label images or a sparse point cloud produced by traditional semantic segmentation and Structure from Motion(SfM) pipelines respectively. We derive a Conditional Random Field (CRF) model defined in the 3D space, that jointly infers the semantic category and occupancy for each voxel. Such a joint inference in the 3D CRF paves the way for more informed priors and constraints, which is otherwise not possible if solved separately in their traditional frameworks. We make use of class specific semantic cues that constrain the 3D structure in areas, where multiview constraints are weak. Our model comprises of higher order factors, which helps when the depth is unobservable.We also make use of class specific semantic cues to reduce either the degree of such higher order factors, or to approximately model them with unaries if possible. We demonstrate improved 3D structure and temporally consistent semantic segmentation for difficult, large scale, forward moving monocular image sequences.

Object Recognition by Sequential Figure-Ground Ranking

We present an approach to visual object-class segmentation and recognition based on a pipeline that combines multiple figure-ground hypotheses with large object spatial support, generated by bottom-up computational processes that do not exploit knowledge of specific categories, and sequential categorization based on continuous estimates of the spatial overlap between the image segment hypotheses and each putative class. We differ from existing approaches not only in our seemingly unreasonable assumption that good object-level segments can be obtained in a feed-forward fashion, but also in formulating recognition as a regression problem. Instead of focusing on a one-vs.-all winning margin that may not preserve the ordering of segment qualities inside the non-maximum (non-winning) set, our learning method produces a globally consistent ranking with close ties to segment quality, hence to the extent entire object or part hypotheses are likely to spatially overlap the ground truth. We demonstrate results beyond the current state of the art for image classification, object detection and semantic segmentation, in a number of challenging datasets including Caltech-101, ETHZ-Shape as well as PASCAL VOC 2009 and 2010.

Multiple Hypothesis Tracking Revisited

This paper revisits the classical multiple hypotheses tracking (MHT) algorithm in a tracking-by-detection framework. The success of MHT largely depends on the ability to maintain a small list of potential hypotheses, which can be facilitated with the accurate object detectors that are currently available. We demonstrate that a classical MHT implementation from the 90s can come surprisingly close to the performance of state-of-the-art methods on standard benchmark datasets. In order to further utilize the strength of MHT in exploiting higher-order information, we introduce a method for training online appearance models for each track hypothesis. We show that appearance models can be learned efficiently via a regularized least squares framework, requiring only a few extra operations for each hypothesis branch. We obtain state-of-the-art results on popular tracking-by-detection datasets such as PETS and the recent MOT challenge.

Latent structured models for human pose estimation

We present an approach for automatic 3D human pose reconstruction from monocular images, based on a discriminative formulation with latent segmentation inputs. We advanced the field of structured prediction and human pose reconstruction on several fronts. First, by working with a pool of figure-ground segment hypotheses, the prediction problem is formulated in terms of combined learning and inference over segment hypotheses and 3D human articular configurations. Beside constructing tractable formulations for the combined segment selection and pose estimation problem, we propose new augmented kernels that can better encode complex dependencies between output variables. Furthermore, we provide primal linear re-formulations based on Fourier kernel approximations, in order to scale-up the non-linear latent structured prediction methodology. The proposed models are shown to be competitive in the HumanEva benchmark and are also illustrated in a clip collected from a Hollywood movie, where the model can infer human poses from monocular images captured in complex environments.

Random Fourier approximations for skewed multiplicative histogram kernels

Approximations based on random Fourier features have recently emerged as an efficient and elegant methodology for designing large-scale kernel machines [4]. By expressing the kernel as a Fourier expansion, features are generated based on a finite set of random basis projections with inner products that are Monte Carlo approximations to the original kernel. However, the original Fourier features are only applicable to translation-invariant kernels and are not suitable for histograms that are always non-negative. This paper extends the concept of translation-invariance and the random Fourier feature methodology to arbitrary, locally compact Abelian groups. Based on empirical observations drawn from the exponentiated χ2 kernel, the state-of-the-art for histogram descriptors, we propose a new group called the skewed-multiplicative group and design translation-invariant kernels on it. Experiments show that the proposed kernels outperform other kernels that can be similarly approximated. In a semantic segmentation experiment on the PASCAL VOC 2009 dataset, the approximation allows us to train large-scale learning machines more than two orders of magnitude faster than previous nonlinear SVMs.

Learning multiple-question decision trees for cold-start recommendation

For cold-start recommendation, it is important to rapidly profile new users and generate a good initial set of recommendations through an interview process --- users should be queried adaptively in a sequential fashion, and multiple items should be offered for opinion solicitation at each trial. In this work, we propose a novel algorithm that learns to conduct the interview process guided by a decision tree with multiple questions at each split. The splits, represented as sparse weight vectors, are learned through an L_1-constrained optimization framework. The users are directed to child nodes according to the inner product of their responses and the corresponding weight vector. More importantly, to account for the variety of responses coming to a node, a linear regressor is learned within each node using all the previously obtained answers as input to predict item ratings. A user study, preliminary but first in its kind in cold-start recommendation, is conducted to explore the efficient number and format of questions being asked in a recommendation survey to minimize user cognitive efforts. Quantitative experimental validations also show that the proposed algorithm outperforms state-of-the-art approaches in terms of both the prediction accuracy and user cognitive efforts.

AMASS: Software for Automatically Validating the Quality of MS/MS Spectrum from SEQUEST Results

Time-consuming and experience-dependent manual validations of tandem mass spectra are usually applied to SEQUEST results. This inefficient method has become a significant bottleneck for MS/MS data processing. Here we introduce a program AMASS (advanced mass spectrum screener), which can filter the tandem mass spectra of SEQUEST results by measuring the match percentage of high-abundant ions and the continuity of matched fragment ions in b, y series. Compared with Xcorr and DeltaCn filter, AMASS can increase the number of positives and reduce the number of negatives in 22 datasets generated from 18 known protein mixtures. It effectively removed most noisy spectra, false interpretations, and about half of poor fragmentation spectra, and AMASS can work synergistically with Rscore filter. We believe the use of AMASS and Rscore can result in a more accurate identification of peptide MS/MS spectra and reduce the time and energy for manual validation.