MM 2010 - PDF Preprint Papers

MM 2010 International Multimedia Conference

Teaser Browsing | Click Here

Title Browsing | Click Here

Wall of Fame | Most Viewed MM-2010 Paper

click to vote

MM
2010
ACM

143views Multimedia» more MM 2010»

KPB-SIFT: a compact local feature descriptor

1 years 5 months ago

Download www3.ntu.edu.sg

Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and object recognition. However, such descriptors are typically of ...

Gangqiang Zhao, Ling Chen, Gencai Chen, Junsong Yu...

claim paper

Read More »

Disclaimer and Copyright Notice

Sciweavers respects the rights of all copyright holders and in this regard, authors are only allowed to share a link to their preprint paper on their own website. Every contribution is associated with a desciptive image. It is the sole responsibility of the authors to ensure that their posted image is not copyright infringing. This service is compliant with IEEE copyright.

Id	Views	Title	Status
1	143	KPB-SIFT: a compact local feature descriptor	claim
2	126	Discriminative codeword selection for image representation	claim
3	105	Hybrid load balancing for online games	claim
4	104	Affective image classification using features inspired by psychology and art theory	claim
5	104	The IMMED project: wearable video monitoring of people with age dementia	claim
6	104	iWalk: a tool for interacting with geo-located data through movement and gesture	claim
7	96	Large-scale music tag recommendation with explicit multiple attributes	claim
8	95	Supervised manifold learning for image and video classification	claim
9	90	FACT: fine-grained cross-media interaction with documents via a portable hybrid paper-laptop interface	claim
10	87	Vlfeat: an open and portable library of computer vision algorithms	claim
11	84	Automatic image tagging via category label and web data	claim
12	83	Multimodal location estimation	claim
13	81	Movie genre classification via scene categorization	claim
14	81	3D ancient mosaics	claim
15	80	TOP-SURF: a visual words toolkit	claim
16	76	Embedded media marker: linking multimedia to paper	claim
17	76	Real-time detection of unusual regions in image streams	claim
18	75	Color and luminance compensation for mobile panorama construction	claim
19	73	Increasing interactivity in street view web navigation systems	claim
20	73	Artistic paper-cut of human portraits	claim
21	72	Crew: cross-modal resource searching by exploiting wikipedia	claim
22	72	Building book inventories using smartphones	claim
23	71	Sirio, orione and pan: an integrated web system for ontology-based video search and annotation	claim
24	71	A framework for photo-quality assessment and enhancement based on visual aesthetics	claim
25	70	Automatic skin enhancement with visible and near-infrared image fusion	claim
26	70	Chromatic perspectives... scaling my art	claim
27	70	Interactive visual object search through mutual information maximization	claim
28	70	TalkMiner: a search engine for online lecture video	claim
29	69	A cognitive approach for effective coding and transmission of 3D video	claim
30	69	iLike: integrating visual and textual features for vertical search	claim
31	69	Eyes do not lie: spontaneous versus posed smiles	claim
32	68	Improving online gaming quality using detour paths	claim
33	68	Landmark image retrieval using visual synonyms	claim
34	68	Non-parametric anomaly detection exploiting space-time features	claim
35	68	Interactive storytelling via video content recombination	claim
36	67	Enhanced exploration of oral history archives through processed video and synchronized text transcripts	claim
37	67	Mobile video streaming in modern wireless networks	claim
38	67	Automatic role recognition based on conversational and prosodic behaviour	claim
39	66	Subjective evaluation of scalable video coding for content distribution	claim
40	66	Changing characters' point of view in interactive storytelling	claim
41	66	The idiap wolf corpus: exploring group behaviour in a competitive role-playing game	claim
42	66	Encounter (resonances)	claim
43	65	Joke-o-Mat HD: browsing sitcoms with human derived transcripts	claim
44	65	The virtual chocolate factory: mixed reality industrial collaboration and control	claim
45	65	Explicit and implicit concept-based video retrieval with bipartite graph propagation model	claim
46	65	A GPU-accelerated face annotation system for smartphones	claim
47	65	Social pixels: genesis and evaluation	claim
48	65	Image classification using the web graph	claim
49	65	MediaPick: tangible semantic media retrieval system	claim
50	64	Mobile product recognition	claim
51	64	A new approach to cross-modal multimedia retrieval	claim
52	64	An immersive system for browsing and visualizing surveillance video	claim
53	64	Making computers look the way we look: exploiting visual attention for image understanding	claim
54	64	Coming together: composition by negotiation	claim
55	64	Keep moving!: revisiting thumbnails for mobile video retrieval	claim
56	63	Understanding the security and robustness of SIFT	claim
57	63	Training data collection system for a learning-based photographic aesthetic quality inference engine	claim
58	63	Topical summarization of web videos by visual-text time-dependent alignment	claim
59	63	Enriching audio-visual chat with conversation-based image retrieval and display	claim
60	63	Webcams in context: web interfaces to create live 3D environments	claim
61	62	Social audio features for advanced music retrieval interfaces	claim
62	62	Analyzing and predicting sentiment of images on the social web	claim
63	62	Quantifying tag representativeness of visual content of social images	claim
64	61	A 3d data intensive tele-immersive grid	claim
65	61	Self-diagnostic peer-assisted video streaming through a learning framework	claim
66	61	Unsupervised summarization of rushes videos	claim
67	61	Image tag refinement towards low-rank, content-tag prior and error sparsity	claim
68	61	Sonify your face: facial expressions for sound generation	claim
69	61	A music search engine for therapeutic gait training	claim
70	60	RAPID: a reliable protocol for improving delay	claim
71	60	TwitterSigns: microblogging on the walls	claim
72	60	Content without context is meaningless	claim
73	60	NudgeCam: toward targeted, higher quality media capture	claim
74	60	Mining and cropping common objects from images	claim
75	59	Coming together: negotiated content by multi-agents	claim
76	59	Multi-exposure imaging on mobile devices	claim
77	58	Restoration of out-of-focus lecture video by automatic slide matching	claim
78	58	Kodak moments and Flickr diamonds: how users shape large-scale media	claim
79	58	Bateau ivre: an artistic markerless outdoor mobile augmented reality installation on a riverboat	claim
80	56	The colour of life: novel visualisations of population lifestyles	claim
81	56	W2Go: a travel guidance system by automatic landmark ranking	claim
82	56	CO3 for ultra-fast and accurate interactive segmentation	claim
83	56	Personalized photograph ranking and selection system	claim
84	56	The wisdom of social multimedia: using flickr for prediction and forecast
85	55	Natural interaction for cultural heritage: the archaeological site of Shawbak	claim
86	55	One person labels one million images	claim
87	55	Using the web to do social science	claim
88	54	Pull-patching: a combination of multicast and adaptive segmented HTTP streaming	claim
89	54	Accelerated IPTV channel change with transcoded unicast bursting	claim
90	54	Negotiating multimedia advertising with attention owners	claim
91	53	Implementation and demonstration of a credit-based home access point	claim
92	53	Image segmentation with patch-pair density priors	claim
93	53	Processing web-scale multimedia data	claim
94	52	TalkMiner: a lecture webcast search engine	claim
95	52	Web-based semantic browsing of video collections using multimedia ontologies	claim
96	52	Tenor: making coding practical from servers to smartphones	claim
97	51	Visual search applications for connecting published works to digital material	claim
98	50	Crowdsourcing rock n' roll multimedia retrieval	claim
99	50	Facilitating interactive search and navigation in videos	claim
100	49	Gaze awareness and interaction support in presentations	claim
101	48	Interactive learning of heterogeneous visual concepts with local features	claim
102	47	"Stray": a new multimedia music composition using the andantephone	claim
103	46	Music recommendation by unified hypergraph: combining social media information and music content	claim
104	46	Photo2Trip: generating travel routes from geo-tagged photos for trip planning	claim
105	43	Trajectory-based visualization of web video topics	claim
106	43	Automatic and manual processes in end-user multimedia authoring tools: where is the balance?	claim
107	38	Sonic visualiser: an open source application for viewing, analysing, and annotating music audio files	claim

Sciweavers

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers