NDLI: Clickage: towards bridging semantic and intent gaps via mining click logs of search engines

Please wait, while we are loading the content...

Multimedia framed

"Wow! you are so beautiful today!"

Robust evaluation for quality of experience in crowdsourcing

Competitive affective gaming: winning with a smile

Topology preserving hashing for similarity search

One-man-band: a touch screen interface for producing live multi-camera sports broadcasts

Social life networks: a multimedia problem?

Learning latent spatio-temporal compositional model for human action recognition

Joserlin: joint request and service scheduling for peer-to-peer non-linear media access

The space between the images

Lecture video segmentation by automatically analyzing the synchronized slides

Real-time salient object detection

Classifying tag relevance with relevant positive and negative examples

Facilitating fashion camouflage art

Waisda?: video labeling game

Human vs machine: establishing a human baseline for multimodal location estimation

Analysis and forecasting of trending topics in online media streams

Towards efficient sparse coding for scalable image annotation

Static saliency vs. dynamic saliency: a comparative study

Using tagged images of low visual ambiguity to boost the learning efficiency of object detectors

The ACM multimedia 2013 art exhibition

4th ACM/IEEE ARTEMIS 2013 international workshop on analysis and retrieval of tracked events and motion in imagery streams

Semantic technologies for multimedia content: foundations and applications

GIANT: geo-informative attributes for location recognition and exploration

Size does matter: how image size affects aesthetic perception?

Tracking-based interaction for object creation in mobile augmented reality

Order preserving hashing for approximate nearest neighbor search

Tele echo tube: beyond cultural and imaginable boundaries

Unveiling the multimedia unconscious: implicit cognitive processes and multimedia content analysis

Exploring discriminative pose sub-patterns for effective action classification

FlashStream: a multi-tiered storage architecture for adaptive HTTP streaming

Activity-aware adaptive compression: a morphing-based frame synthesis application in 3DTI

Kanji snap: an OCR-based smartphone application for learning Japanese kanji characters

Non-rigid target tracking based on 'flow-cut' in pair-wise frames with online hough forests

An efficient image homomorphic encryption scheme with small ciphertext expansion

GamingAnywhere: an open-source cloud gaming testbed

Cross-media semantic representation via bi-directional learning to rank

Why not, WINE?: towards answering why-not questions in social image search

Learning with limited and noisy tagging

Building holistic descriptors for scene recognition: a multi-objective genetic programming approach

Projective identity and procedural rhetoric in educational multimedia: towards the enrichment of programming self-concept and growth mindset with fantasy role-play

Workshop summary for the 3rd international audio/visual emotion challenge and workshop (AVEC'13)

Towards next generation multimedia recommendation systems

Online human gesture recognition from motion data streams

Non-reference audio quality assessment for online live music recordings

Physical modelling and supervised training of a virtual string quartet

Linear cross-modal hashing for efficient multimedia search

eHeritage of shadow puppetry: creation and manipulation

Large-scale visual sentiment ontology and detectors using adjective noun pairs

Human activities recognition using depth images

Early event-driven (EED) RTCP feedback for rapid IDMS

Flickr-tag prediction using multi-modal fusion and meta information

Mobile video browsing with the ThumbBrowser

Object coding on the semantic graph for scene classification

Large-scale multimedia content analysis using scientific workflows

The social signal interpretation (SSI) framework: multimodal signal processing and recognition in real-time

Listen, look, and gotcha: instant video search with mobile phones by layered audio-video indexing

Automatic generation of social media snippets for mobile browsing

Picture tags and world knowledge: learning tag relations from visual semantic sources

Scale based region growing for scene text detection

Recognition of complex events in open-source web-scale videos: a bottom up approach

Workshop summary for the 5th international workshop on multimedia for cooking and eating activities (CEA'13)

Crowdsourcing for multimedia research

Attribute-augmented semantic hierarchy: towards bridging semantic gap and intention gap in image retrieval

Enabling low bitrate mobile visual recognition: a performance versus bandwidth evaluation

Using quadratic programming to estimate feature relevance in structural analyses of music

Online multimodal deep similarity learning with application to image retrieval

Hybrid robotic/virtual pan-tilt-zom cameras for autonomous event recording

Indexing billions of images for sketch-based retrieval

We are not equally negative: fine-grained labeling for multimedia event detection

Orchestration: tv-like mixing grammars applied to video-communication for social groups

Structured exploration of who, what, when, and where in heterogeneous multimedia news sources

Physiognomy master: a novel personality analysis system based on facial features

Beyond bag of words: image representation in sub-semantic space

Recent developments in openSMILE, the munich open-source multimedia feature extractor

Parallel field alignment for cross media retrieval

Temporal encoded F-formation system for social interaction detection

Annotation for free: video tagging by mining user search behavior

Visual interestingness in image sequences

Motion compensated compressed domain watermarking

ACM multimedia 2013 workshop on crowdsourcing for multimedia

Massive-scale multimedia semantic modeling

Clickage: towards bridging semantic and intent gaps via mining click logs of search engines

Towards a comprehensive computational model foraesthetic assessment of videos

LAVES: an instant mobile video search system based on layered audio-video indexing

Speaking swiss: languages and venues in foursquare

ImproveMyCity: an open source platform for direct citizen-government communication

Social interaction detection using a multi-sensor approach

Second ACM multimedia workshop on geotagging and its applications in multimedia (GeoMM 2013)

Social interactions over geographic-aware multimedia systems

Latent feature learning in social media network

Multi-factor segmentation for topic visualization and recommendation: the MUST-VIS system

Freesound technical demo

What are the distance metrics for local features?

LIRE: open source image retrieval in Java

Virtual director technology for social video communication and live event broadcast production

Fourth international workshop on human behavior understanding (HBU 2013)

Multimedia information retrieval: music and audio

Beauty is here: evaluating aesthetics in videos using multimodal features and free training data

Visualizing web mash-ups for in-situ vision-based mobile AR applications

Salient object detection in videos by optimal spatio-temporal path discovery

Golden retriever: a Java based open source image retrieval engine

Gesture--sound mapping by demonstration in interactive music systems

Immersive media experiences: immersiveme 2013 workshop at ACM multimedia

Blending the physical and the virtual in music technology: from interface design to multi-modal signal processing

Metadata enrichment for news video retrieval: a graph-based propagation approach

repoVizz: a framework for remote storage, browsing, annotation, and exchange of multi-modal data

Multiview semi-supervised ranking for automatic image annotation

Stage framework: an HTML5 and CSS3 framework for digital publishing

Learning representations for affective video understanding

The third ACM international workshop on interactive multimedia on mobile and portable devices (IMMPD'13)

Privacy concerns of sharing multimedia in social networks

Human action recognition by fast dense trajectories

Small objects query suggestion in a large web-image collection

How do we deep-link?: leveraging user-contributed time-links for non-linear video access

ESSENTIA: an open-source library for sound and music analysis

Context-aware gesture recognition in classical music conducting

2nd international workshop on socially-aware multimedia (SAM'13)

Scalable training with approximate incremental laplacian eigenmaps and PCA

Video2Sentence and vice versa

Compact bag-of-words visual representation for effective linear classification

SCReen adjusted panoramic effect: SCRAPE

Bringing the sport stadium atmosphere to remote fans

Summary abstract for the 2nd ACM international workshop on multimedia analysis for ecological data

Estimating beauty ratings of videos using supervoxels

A tool for catching back your preferred videos from physical collages

Large-scale web video shot ranking based on visual features and tag co-occurrence

Orcc: multimedia development made easy

Automatic melodic and structural analysis of music material for enriched concert related experiences

ACM MM MIIRH 2013: workshop on multimedia indexing and information retrieval for healthcare

Action recognition using invariant features under unexampled viewing conditions

Pl@ntNet mobile app

Locality preserving verification for image search

Design, development and evaluation of an adaptive and standardized RTP/RTCP-based IDMS solution

Summary abstract for the 1st ACM international workshop on personal data meets distributed multimedia

Search-based relevance association with auxiliary contextual cues

Determining exposure values from HDR histograms for smartphone photography

Undo the codebook bias by linear transformation for visual applications

Visual object analysis using regions and interest points

Image search by graph-based label propagation with image representation from DNN

Semantic dispatching of multimedia news with MEWS

GLocal structural feature selection with sparsity for multimedia data understanding

Cloud based multimedia analytic platform

Score-informed audio decomposition and applications

Adaptable and personalized game-based training system for fall prevention

Background subtraction via coherent trajectory decomposition

AdVisual: a visual-based advertising system

Motion matters: a novel framework for compressing surveillance videos

Multi-screen cloud social TV: transforming TV experience into 21st century

Spatialized audio multiparty teleconferencing with commodity miniature microphone array

"Wow! you are so beautiful today!"

Learning articulated body models for people re-identification

OSCOR: an orientation sensor data correction system for mobile generated contents

Facial landmark localization based on hierarchical pose regression with cascaded random ferns

OTMedia: the French TransMedia news observatory

Image context discovery from socially curated contents

TEEVE endpoint: towards the ease of 3D tele-immersive application development

Moment feature based forensic detection of resampled digital images

eHeritage of shadow puppetry: creation and manipulation

Towards precise POI localization with social media

Gesture-based control of physical modeling sound synthesis: a mapping-by-demonstration approach

Sim-min-hash: an efficient matching technique for linking large image collections

News rover: exploring topical structures and serendipity in heterogeneous multimedia news

Recognizing the royals: leveraging computerized face recognition for identifying subjects in ancient artworks

A novel framework for collaborative video recommendation, interest discovery and friendship suggestion based on semantic profiling

CollARt: a tool for creating 3D photo collages using mobile augmented reality

euTV: a system for media monitoring and publishing

Spatio-temporal fisher vector coding for surveillance event detection

CAMMA: contextual advertising system for multimodal news aggregations

Efficient image and tag co-ranking: a bregman divergence optimization method

Flarty: recommending art routes using check-ins latent topics

Real-time privacy-preserving moving object detection in the cloud

SentiBank: large-scale ontology and classifiers for detecting sentiment and emotions in visual content

With one look: robust face recognition using single sample per person

Augmented and interactive video playback based on global camera pose

Weakly-supervised multi-class object detection using multi-type 3D features

EigenNews: a personalized news video delivery platform

Querying for video events by semantic signatures from few examples

NovaEmötions: winning with a smile

Towards cover group thumbnailing

Tell me what happened here in history

Multi-feature canonical correlation analysis for face photo-sketch image retrieval

Group TV: a cloud based social TV for group social experience

Hand and foot gesture interaction for handheld devices

GeSoDeck: a geo-social event detection and tracking system

AirTouch panel: a re-anchorable virtual touch panel

Stereotime: a wireless 2D and 3D switchable video communication system

Creation of individual photo selections: read preferences from the users' eyes

MagicBrush: image search by color sketch

Strong geometrical consistency in large scale partial-duplicate image search

Jiku director: a mobile video mashup system

Segmental multi-way local pooling for video recognition

WeCard: a multimodal solution for making personalized electronic greeting cards

Efficient video quality assessment based on spacetime texture representation

Fitted spectral hashing

Using emotional context from article for contextual music recommendation

Revisiting the VLAD image representation

Human behavior sensing for tag relevance assessment

Robust facial expressions recognition using 3D average face and ameliorated adaboost

Visual business recognition: a multimodal approach

3D view synthesis with inter-view consistency

Improving event detection using related videos and relevance degree support vector machines

Consistent stereo image editing

Superpixel segmentation based structural scene recognition

Evaluation of salient point methods

Cross-media topic mining on wikipedia

A multigrid approach for bandwidth and display resolution aware streaming of 3D deformations

Error recovered hierarchical classification

Time matters!: capturing variation in time in video using fisher kernels

A multimodal probabilistic model for gesture--based control of sound synthesis

Modeling local descriptors with multivariate gaussians for object and scene recognition

Anchor concept graph distance for web image re-ranking

Violence detection in hollywood movies by the fusion of visual and mid-level audio cues

A 3D tele-immersion streaming approach using skeleton-based prediction

Fast image/video collection summarization with local clustering

Spot the differences: from a photograph burst to the single best picture

Semantic pooling for complex event detection

SwarmVision: autonomous aesthetic multi-camera interaction

Segmenting music through the joint estimation of keys, chords and structural boundaries

3D teleimmersive activity classification based on application-system metadata

Object co-segmentation via discriminative low rank matrix recovery

πLDA: document clustering with selective structural constraints

Con-text: text detection using background connectivity for fine-grained object classification

Relative spatial features for image memorability

Automatic Egyptian hieroglyph recognition by retrieving images as texts

Query-dependent visual dictionary adaptation for image reranking

Correlated-spaces regression for learning continuous emotion dimensions

RealSense: directional interaction for proximate mobile sharing using built-in orientation sensors

Understanding and classifying image tweets

User interest and social influence based emotion prediction for individuals

Bimodal log-linear regression for fusion of audio and visual features

Clickage: towards bridging semantic and intent gaps via mining click logs of search engines

Content Provider	ACM Digital Library
Author	Ye, Ming Li, Jin Wang, Jingdong Wang, Jing Hua, Xian-Sheng Rui, Yong Yang, Linjun Wang, Kuansan
Abstract	The semantic gap between low-level visual features and high-level semantics has been investigated for decades but still remains a big challenge in multimedia. When "search" became one of the most frequently used applications, "intent gap", the gap between query expressions and users' search intents, emerged. Researchers have been focusing on three approaches to bridge the semantic and intent gaps: 1) developing more representative features, 2) exploiting better learning approaches or statistical models to represent the semantics, and 3) collecting more training data with better quality. However, it remains a challenge to close the gaps. In this paper, we argue that the massive amount of click data from commercial search engines provides a data set that is unique in the bridging of the semantic and intent gap. Search engines generate millions of click data (a.k.a. image-query pairs), which provide almost "unlimited" yet strong connections between semantics and images, as well as connections between users' intents and queries. To study the intrinsic properties of click data and to investigate how to effectively leverage this huge amount of data to bridge semantic and intent gap is a promising direction to advance multimedia research. In the past, the primary obstacle is that there is no such dataset available to the public research community. This changes as Microsoft has released a new large-scale real-world image click data to public. This paper presents preliminary studies on the power of large-scale click data with a variety of experiments, such as building large-scale concept detectors, tag processing, search, definitive tag detection, intent analysis, etc., with the goal to inspire deeper researches based on this dataset.
Starting Page	243
Ending Page	252
Page Count	10
File Format	PDF
ISBN	9781450324045
DOI	10.1145/2502081.2502283
Language	English
Publisher	Association for Computing Machinery (ACM)
Publisher Date	2013-10-21
Publisher Place	New York
Access Restriction	Subscribed
Subject Keyword	Image search Dataset Image understanding
Content Type	Text
Resource Type	Article

Central Library (ISO-9001:2015 Certified)
Indian Institute of Technology Kharagpur
Kharagpur, West Bengal, India | PIN - 721302

See location in the Map
03222 282435
Mail: support@ndl.gov.in

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in