Partial Instances Research Articles

Enhancing identification for person search with multi-scale multi-grained representation learning

Person Search aims to simultaneously address Person Detection and Person Re-ID. There are various challenges in person search such as significant scale variations, occlusions, and partial instances. In this paper, we propose a Multi-Scale Multi-Grained (MSMG) sequential network for end-to-end person search, intended to alleviate these issues. To generate re-id representations robust to scale changes, MSMG leverages multi-scale RoI features and aggregates them with a proposed Multi-Scale feature Aggregation Encoder (MSAE). In this way, the aggregated multi-scale re-id features are enriched with more semantic information and detailed information, thereby being more discriminative for identification. Moreover, to produce re-id representations more robust to occlusions and partial instances, MSMG introduces a Multi-Grained feature Learning Decoder (MGLD) focused on multi-grained feature learning. MGLD adaptively decodes multi-grained re-id representations with more accurate semantic information through a regional deformable cross-attention module. Finally, the multi-scale multi-grained re-id representation substantially improves the identification accuracy under challenging cases. Through comprehensive experiments, we demonstrate that our method achieves state-of-the-art performance on two benchmark datasets. On the challenging PRW benchmark, MSMG obtains the best-reported results with a mean average precision (mAP) score of 61.3%.

Compound Weakly Supervised Clustering.

Clustering is a fundamental and important step in many image processing tasks, such as face recognition and image segmentation. The performance of clustering can be largely enhanced if relevant weak supervision information is appropriately exploited. To achieve this goal, in this paper, we propose the Compound Weakly Supervised Clustering (CSWC) method. Concretely, CSWC incorporates two types of widely available and easily accessed weak supervision information from the label and feature aspects, respectively. To be specific, at the label level, the pairwise constraints are utilized as a kind of typical weak label supervision information. At the feature level, the partial instances collected from multiple perspectives have internal consistency and they are regarded as weak structure supervision information. To achieve a more confident clustering partition, we learn a unified graph with its similarity matrix to incorporate the above two types of weak supervision. On one hand, this similarity matrix is constructed by self-expression across the partial instances collected from multiple perspectives. On the other hand, the pairwise constraints, i.e., must-links and cannot-links, are considered by formulating a regularizer on the similarity matrix. Finally, the clustering results can be directly obtained according to the learned graph, without performing additional clustering techniques. Besides evaluating CSWC on 7 benchmark datasets, we also apply it to the application of face clustering in video data since it has vast application potentiality. Experimental results demonstrate the effectiveness of our algorithm in both incorporating compound weak supervision and identifying faces in real applications.

Post-truth as a syndrome of Digital Age: ultimate understanding of the phenomenon and scenarios of the future

The subject field of this research is the combination of cultural phenomena, which correlate with the initially highlighted concept of “post-truth” through generalization of its criteria. The traditionally narrow understanding of post-truth is associated with news reports of mass media. However, the distortion of actual picture, using the techniques of heuristic rhetoric and mechanisms that instigate cognitive biases is a more common situation in modern society, which unites various communication phenomena, touches upon news and everyday communication, artistic endeavor, and many other areas. The specific subject of research is the range of possible scenarios of social development depending on its response to proliferation of the phenomena that comprise the cultural-communication complex of “post-truth”. This article is the first attempt of scientific summary of the phenomenal picture of post-truth based on the competent expansion of the criteria from the partial instances to the general mechanisms. Partial criteria, such as neglecting objective factors in the report, appeal to human values and ideologies, use of emotional pressure for substantiating own opinion, the author replaces with the general: media distortion of reality as a goal of report, use of cognitive biases, use of mechanisms of heuristics. Based on the highlighted criteria, the author analyzes the question of semantic and cultural correlation with post-truth of such as the phenomena as the fan theories of two types, litbaits, pop science, folk history, astroturfing, fan fakes, clickbaits, narrative journalism, etc. Scientific novelty also consists in outlining the possible scenarios for social development and its communication environment depending on the strategies of response to expansion of the sphere of post-truth.

Multi-view clustering on data with partial instances and clusters

Most multi-view clustering algorithms apply to data with complete instances and clusters in the views. Recently, multi-view clustering on data with partial instances has been studied. In this paper, we study the more general version of the problem, i.e., multi-view clustering on data with partial instances and clusters in the views. We propose a non-negative matrix factorization (NMF) based algorithm. For the special case with partial instances, it introduces an instance-view-indicator matrix to indicate whether an instance exists in a view. Then, it maps the instances representing the same object to the same vector, and maps the instances representing different objects to different vectors. For the general case with partial instances and clusters, it further introduces a cluster-view-indicator matrix to indicate whether a cluster exists in a view. In each view, it also maps the instances representing the same object to the same vector, but it further makes the elements of the vector 0 if the elements correspond to missing clusters. Then it minimizes the disagreements between the approximated indicator vectors of instances representing the same object. Experimental results show that the proposed algorithm performs well on data with partial instances and clusters, and outperforms existing algorithms on data with partial instances.

Structural Process Pattern Matching Based on Graph Morphism Detection

Context: Processes are central to the operation of many systems or organizations. Process-centric systems, ranging from enterprise workflow systems to open distributed service compositions, have significantly increased in number and complexity. Objective: Designers of process-centric systems can benefit from process abstractions (including patterns) capturing and allowing the reuse of designs for frequent operational problems. Existing process patterns detection techniques have efficiency problems and difficulties to identify partial and inexact pattern instances. Method: We propose a process pattern detection technique based on a family of subgraph matching algorithms. The algorithms implement surjective graph morphism detection and a mechanism to incorporate semantic similarity computation for types and attributes of process graph elements. Results: Efficiency is addressed using simplified data structures, reducing the search space and its exploration. Match accuracy and time-complexity are demonstrated in an experimental study. Conclusions: Using process patterns allows business and technical processes to be provided as sharable service resources. Patterns can help to manage processes as configurable resources where a pattern can define a family of concrete customizable processes.

Using Boolean Satisfiability Solving for Pairwise Test Generation from Cause-Effect Graphs: Comparison of Three Approaches

Cause-effect graphs can be used for specifying safety critical systems including avionics control software that are often intended to satisfy Boolean expression. Using cause-effect graphs for requirements-based testing demands the ability of dealing with various constraints in cause-effect graphs. Due to its rapid advance, Boolean Satisfiability (SAT) solving seems to be a promising approach for constraint handling. In this paper, we present three approaches using SAT solving for pairwise test generation from cause-effect graphs. One is an ideal approach that tries to obtain a minimal set of tests. Another approach focuses on breaking the problem to smaller solvable problems to scale the applicability of SAT solving. The other makes full use of a partial instance that forms a part of a solution known priori. We compare the three approaches in terms of the number of generated pairwise tests and fault detection capability. Comparison results show that an approach using partial instances can generate less number of pairwise tests than the other two approaches without degrading fault detection capability.

Deriving Information from Sampling and Diving

We investigate the impact of information extracted from sampling and diving on the solution of Constraint Satisfaction Problems (CSP). A sample is a complete assignment of variables to values taken from their domain according to a given distribution. Diving consists in repeatedly performing depth first search attempts with random variable and value selection, constraint propagation enabled and backtracking disabled; each attempt is called a dive and, unless a feasible solution is found, it is a partial assignment of variables (whereas a sample is a -possibly infeasible- complete assignment). While the probability of finding a feasible solution via sampling or diving is negligible if the problem is difficult enough, samples and dives are very fast to generate and, intuitively, even when they are infeasible, they can provide some statistical information on search space structure. The aim of this paper is to understand to what extent it is possible to support the CSP solving process with information derived from sampling and diving. In particular, we are interested in extracting from samples and dives precise indications on the quality of individual variable-value assignments with respect to feasibility. We formally prove that even uniform sampling could provide precise evaluation of the quality of single variable-value assignments; as expected, this requires huge sample sizes and is therefore not useful in practice. On the contrary, diving is much better suited for assignment evaluation purposes. We undertake a thorough experimental analysis on a collection of Partial Latin Square and Car Sequencing instances to assess the quality of information provided by dives. Dive features are identified and their impact on search is evaluated. Results show that diving provides information that can be fruitfully exploited.

Decomposition systems on spaces with a measure

We propose a general construction of various decomposition systems for square-integrable functions, partial instances, of which are continuous wavelet decompositions. We give an analogue of the Parseval-Plancherel identity and a reconstruction formula as well as a number of examples of decomposition systems.

On a saline substance from mount vesuvius

From the strong evidence we have that a very large proportion of the world, as we now see it, has at some period been either in a state of actual combustion, or has felt the effects of heat, a high interest, says the author, attaches itself to volcanoes and their ejections, as partial instances of similar operations now going on. In support of the igneous origin of primitive strata, it is observed, not only that no crystal imbedded in them contains water, but that none of the materials of the strata contain water in any state.