Object recognition and content

2011 ◽  
Vol 2 (2) ◽  
pp. 207-226
Author(s):  
LYDIA SÁNCHEZ ◽  
MANUEL CAMPOS
Keyword(s):  
Object Recognition ◽  
Direct Reference ◽  
Truth Conditions ◽  
Attitude Reports ◽  
Central Elements ◽  
Recognition Of Objects ◽  
Truth Value

Puzzles concerning attitude reports are at the origin of traditional theories of content. According to most of these theories, content has to involve some sort of conceptual entities, like senses, which determine reference. Conceptual views, however, have been challenged by direct reference theories and informational perspectives on content. In this paper we lay down the central elements of the more relevant strategies for solving cognitive puzzles. We then argue that the best solution available to those who maintain a view of content as truth conditions is to abandon the idea that content is the only element of mental attitudes that can make a difference as to the truth value of attitude reports. We finally resort to means of recognition of objects as one obvious element that helps explain differences in attitudes.

scholarly journals Indexical Sinn: Fregeanism versus Millianism

2014 ◽  
Vol 26 (39) ◽  
pp. 465
Author(s):  
João Branquinho
Keyword(s):  
Propositional Attitude ◽  
Proper Names ◽  
Direct Reference ◽  
Cognitive Significance ◽  
De Re ◽  
General Conception ◽  
Attitude Reports ◽  
Singular Reference ◽  
Reference Theory ◽  
Careful Assessment

This paper discusses two notational variance views with respect to indexical singular reference and content: the view that certain forms of Millianism are at bottom notational variants of a Fregean theory of reference, the Fregean Notational Variance Claim; and the view that certain forms of Fregeanism are at bottom notational variants of a direct reference theory, the Millian Notational Variance Claim. While the former claim rests on the supposition that a direct reference theory could be easily turned into a particular version of a neo-Fregean one by showing that it is bound to acknowledge certain senselike entities, the latter claim is based upon the supposition that a neo-Fregean theory could be easily turned into a particular version of a Millian one by showing that De Re senses are theoretically superfluous and hence eliminable. The question how many accounts of singular reference and content are we confronted with here — Two different (and mutually antagonistic) theories? Or just two versions of what is in essence the same theory? — is surely of importance to anyone interested in the topic. And this question should be answered by means of a careful assessment of the soundness of each of the above claims. Before trying to adjudicate between the two accounts, one would naturally want to know whether or not there are indeed two substantially disparate accounts. Grosso modo, if the Fregean Claim were sound then we would have a single general conception of singular reference to deal with, viz. Fregeanism; likewise, if the Millian Claim were sound we would be facing a single general conception of singular reference, viz. Millianism. My view is that both the Fregean Notational Variance Claim and its Millian counterpart are wrong, though naturally on different grounds. I have argued elsewhere that the Fregean Notational Variance Claim - considered in its application to the semantics of propositional-attitude reports involving proper names — is unsound. I intend tosupplement in this paper such a result by trying to show that the Millian Claim - taken in its application to the semantics of indexical expressions — should also be rated as incorrect. I focus on a certain set of arguments for the Millian Claim, arguments which I take as adequately representing the general outlook of the Millian theorist with respect to neo-Fregeanism about indexicals and which involve issues about the cognitive significance of sentences containing indexical terms.

Walter Burley on Co-Signification in Opaque Contexts

2020 ◽  
pp. 221-247
Author(s):  
Nathaniel Bulthuis
Keyword(s):  
Semantic Analysis ◽  
Propositional Attitude ◽  
Direct Reference ◽  
Attitude Reports ◽  
The World ◽  
The Face ◽  
Walter Burley

Foreshadowing in many ways theories of direct reference popular today, Walter Burley (died c. 1345) favors a theory of direct signification, according to which names directly signify things in the world. But he recognizes that opaque contexts, such as propositional attitude reports, represent a challenge to that theory. In response, Burley develops a sophisticated account of our noetic states, one according to which those states can be individuated more finely than in terms of their contents. Paired with a certain semantic analysis of propositional attitude reports, that account of our noetic states is ready-made to accommodate Burley’s commitment to direct signification even in the face of opacity considerations.

A Probabilistic Neural Network-Based Module for Recognition of Objects from their 3-D Images

2013 ◽  
Vol 2 (2) ◽  
pp. 66-79 ◽  
Author(s):  
Onsy A. Abdel Alim ◽  
Amin Shoukry ◽  
Neamat A. Elboughdadly ◽  
Gehan Abouelseoud
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Decision Making ◽  
Pattern Recognition ◽  
Object Recognition ◽  
Probabilistic Neural Network ◽  
Training Procedure ◽  
Generalization Capability ◽  
Mine Detection ◽  
Recognition Of Objects

In this paper, a pattern recognition module that makes use of 3-D images of objects is presented. The proposed module takes advantage of both the generalization capability of neural networks and the possibility of manipulating 3-D images to generate views at different poses of the object that is to be recognized. This allows the construction of a robust 3-D object recognition module that can find use in various applications including military, biomedical and mine detection applications. The paper proposes an efficient training procedure and decision making strategy for the suggested neural network. Sample results of testing the module on 3-D images of several objects are also included along with an insightful discussion of the implications of the results.

A Hippocampal Signature of Perceptual Learning in Object Recognition

2015 ◽  
Vol 27 (4) ◽  
pp. 787-797 ◽  
Author(s):  
Matthias Guggenmos ◽  
Marcus Rothkirch ◽  
Klaus Obermayer ◽  
John-Dylan Haynes ◽  
Philipp Sterzer
Keyword(s):  
Object Recognition ◽  
Perceptual Learning ◽  
Transfer Of Learning ◽  
Behavioral Training ◽  
Enhancing Effect ◽  
Monetary Rewards ◽  
Before And After ◽  
Perceptual Performance ◽  
Recognition Of Objects

Perceptual learning is the improvement in perceptual performance through training or exposure. Here, we used fMRI before and after extensive behavioral training to investigate the effects of perceptual learning on the recognition of objects under challenging viewing conditions. Objects belonged either to trained or untrained categories. Trained categories were further subdivided into trained and untrained exemplars and were coupled with high or low monetary rewards during training. After a 3-day training, object recognition was markedly improved. Although there was a considerable transfer of learning to untrained exemplars within categories, an enhancing effect of reward reinforcement was specific to trained exemplars. fMRI showed that hippocampus responses to both trained and untrained exemplars of trained categories were enhanced by perceptual learning and correlated with the effect of reward reinforcement. Our results suggest a key role of hippocampus in object recognition after perceptual learning.

Frege's Detour

2019 ◽  
Author(s):  
John Perry
Keyword(s):  
Philosophy Of Language ◽  
Propositional Attitude ◽  
Propositional Attitudes ◽  
Truth Conditions ◽  
Cognitive States ◽  
Indirect Discourse ◽  
Attitude Reports ◽  
Sense And Reference ◽  
In Virtue Of ◽  
Indirect Reference

I argue that Frege’s treatment of propositional attitudes in “On Sense and Reference” put the philosophy of language on a detour. His doctrine of “indirect reference” reflected and reinforced the view that beliefs, desires, etc. consist in having relations to propositions. According to this doctrine expressions in embedded sentences in indirect discourse and propositional attitude reports do refer as they do when unembedded, but instead refer to their ordinary senses, so sentences refer to Thoughts, Frege’s version of what are now callled general or qualitative propositions. Davidson call this move abandoning “semantic innocence” which is the view that such embedded sentences work as they usually do. I agree with Davidson, that semantic innocence should not be abandonned. I argue that such cognitive states have truth-conditions in virtue of their causal and informational roles, which can be encoded in a variety of ways for different purposes, and provide a better explanation of the considerations that drove Frege to abandon innocence. I trace the problems I see to Frege’s abandonment of the framework of his early work, the Begriffsschrift. I argue that by adding the levels of senses and Thoughts to his Begriffsschriftframework, and retaining “circumstances” as the referents of sentences containing singular terms, Frege could have avoided the doctrine of indirect reference, and philosophy could have taken a different path.

scholarly journals Distributed Architecture to Integrate Sensor Information: Object Recognition for Smart Cities

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 112 ◽  
Author(s):  
Jose-Luis Poza-Lujan ◽  
Juan-Luis Posadas-Yagüe ◽  
José-Enrique Simó-Ten ◽  
Francisco Blanes
Keyword(s):  
Object Recognition ◽  
Smart Cities ◽  
Image Sensors ◽  
Sensor Data ◽  
Intelligent Environments ◽  
Distributed Information ◽  
Information Object ◽  
Environment Map ◽  
Recognition Of Objects ◽  
Integrate Sensor

Object recognition, which can be used in processes such as reconstruction of the environment map or the intelligent navigation of vehicles, is a necessary task in smart city environments. In this paper, we propose an architecture that integrates heterogeneously distributed information to recognize objects in intelligent environments. The architecture is based on the IoT/Industry 4.0 model to interconnect the devices, which are called smart resources. Smart resources can process local sensor data and offer information to other devices as a service. These other devices can be located in the same operating range (the edge), in the same intranet (the fog), or on the Internet (the cloud). Smart resources must have an intelligent layer in order to be able to process the information. A system with two smart resources equipped with different image sensors is implemented to validate the architecture. Our experiments show that the integration of information increases the certainty in the recognition of objects by 2–4%. Consequently, in intelligent environments, it seems appropriate to provide the devices with not only intelligence, but also capabilities to collaborate closely with other devices.

Stimulus Context and View Dependence in Object Recognition

Perception ◽  
1998 ◽  
Vol 27 (1) ◽  
pp. 47-68 ◽  
Author(s):  
Fiona N Newell
Keyword(s):  
Object Recognition ◽  
Recognition Performance ◽  
Target Object ◽  
Stimulus Context ◽  
Representational Space ◽  
Small Feature ◽  
Recognition Of Objects

The effect of stimulus factors such as interobject similarity and stimulus density on the recognition of objects across changes in view was investigated in five experiments. The recognition of objects across views was found to depend on the degree of interobject similarity and on stimulus density: recognition was view dependent when both interobject similarity and stimulus density were high, irrespective of the familiarity of the target object. However, when stimulus density or interobject similarity was low recognition was invariant to viewpoint. It was found that recognition was accomplished through view-dependent procedures when discriminability between objects was low. The findings are discussed in terms of an exemplar-based model in which the dimensions used for discriminating between objects are optimised to maximise the differences between the objects. This optimisation process is characterised as a perceptual ‘ruler’ which measures interobject similarity by stretching across objects in representational space. It is proposed that the ‘ruler’ optimises the feature differences between objects in such a way that recognition is view invariant but that such a process incurs a cost in discriminating between small feature differences, which results in view-dependent recognition performance.

scholarly journals On the necessity of recurrent processing during object recognition: it depends on the need for scene segmentation

2020 ◽  
Author(s):  
Noor Seijdel ◽  
Jessica Loke ◽  
Ron van de Klundert ◽  
Matthew van der Meer ◽  
Eva Quispel ◽  
...  
Keyword(s):  
Object Recognition ◽  
Network Performance ◽  
Target Object ◽  
Feed Forward ◽  
Complex Scenes ◽  
Recurrent Processing ◽  
Ground Segmentation ◽  
Recognition Of Objects ◽  
Evoked Response Potentials ◽  
Time Point

AbstractWhile feed-forward activity may suffice for recognizing objects in isolation, additional visual operations that aid object recognition might be needed for real-world scenes. One such additional operation is figure-ground segmentation; extracting the relevant features and locations of the target object while ignoring irrelevant features. In this study of 60 participants, we show objects on backgrounds of increasing complexity to investigate whether recurrent computations are increasingly important for segmenting objects from more complex backgrounds. Three lines of evidence show that recurrent processing is critical for recognition of objects embedded in complex scenes. First, behavioral results indicated a greater reduction in performance after masking objects presented on more complex backgrounds; with the degree of impairment increasing with increasing background complexity. Second, electroencephalography (EEG) measurements showed clear differences in the evoked response potentials (ERPs) between conditions around 200ms - a time point beyond feed-forward activity and object decoding based on the EEG signal indicated later decoding onsets for objects embedded in more complex backgrounds. Third, Deep Convolutional Neural Network performance confirmed this interpretation; feed-forward and less deep networks showed a higher degree of impairment in recognition for objects in complex backgrounds compared to recurrent and deeper networks. Together, these results support the notion that recurrent computations drive figure-ground segmentation of objects in complex scenes.

scholarly journals The search for truth: Appositives weigh in

2019 ◽  
Vol 29 ◽  
pp. 180
Author(s):  
Margaret Kroll ◽  
Amanda Rysling
Keyword(s):  
Experimental Work ◽  
Speech Act ◽  
Theoretical Point ◽  
Truth Conditions ◽  
Value Judgments ◽  
Complex Sentences ◽  
Highly Sensitive ◽  
Truth Conditional ◽  
Task Features ◽  
Truth Value

The semantic and pragmatic contribution of appositives to their containing sentence is a subject of continuing debate. While unidimensional semantic accounts propose that appositives contribute their truth conditions to their containing sentence, multidimensional accounts predict that they do not. In three experiments, we directly compared judgments of the truth of sentences containing appositives and sentences containing conjunctions. Our findings contribute both a method- ological and a theoretical point. First, we show that no conclusions about the truth-conditional contributions of appositives can be drawn from experimental work without further investigation of how participants provide truth value judgments for complex sentences. Second, we show that while appositives appear to contribute truth values to their containing sentences, participants are highly sensitive to task features when they compute the truth value of sentences with appositives and also, crucially, with conjunctions. Specifically, we show that both sentences containing appositives and those containing conjunctions can be judged true even when the appositive or one conjunct is patently false. We conclude that it is unlikely that these results reflect semantic judgments, and suggest that they reflect truth only at the speech-act level.

scholarly journals Ascent and fallacy of semantic descent

2021 ◽  
Vol 64 (4) ◽  
pp. 99-109
Author(s):  
Jelena Pavlicic
Keyword(s):  
Knowledge Attribution ◽  
Methodological Framework ◽  
Truth Conditions ◽  
Key Points ◽  
Truth Value ◽  
Knowledge Claims ◽  
Analysis Point

A substantial share of recent semantic and epistemological debates is focused on the description and analysis of ways to defend the thesis that changes in truth conditions of knowledge claims enfold on the back of subjective parameters. The broad popularity of this thesis - which runs contrary to the notion that variation in truth value is independent of informal factors - is a result of the belief that it offers a sustainable methodological framework for responding to the skeptic?s doubts. This paper begins by sketching the key points which serve to illustrate the nature of this antiskeptical strategy. Further on, the paper describes three problems the strategy faces, as well as attempts to address them by articulating a meta-linguistical thesis on truth conditions of knowledge attribution sentences. The aim of the paper is to reconstruct the project of the meta-linguistical analysis, point to its specifics and flaws, and answer the question of what it achieves.

Sign in / Sign up

Export Citation Format

Share Document