1. An information processing apparatus including a processor and a memory for processing first information and second information, each information generated in a production of content data and containing information relating to the content data, the information processing apparatus comprising:
adding means for adding, to the second information, first linking information linking the first information, and adding, to the second information, identification information of material data to be edited; and
generating means for generating second linking information that links the second information to the first information,
wherein the first information comprises unedited material data prior to editing;
generating means for generating second information comprising a composition table in response to input from a user,
wherein the composition table serves as a plan for editing the first information and the composition table is linked to the first information and the composition table identifies an in point and an out point of an editing process in the first information,
wherein an edit list is generated based on the composition table, comprising an edit description of the editing process and is linked to the first information,
wherein the composition table is acquired based on identification information of the composition table added to the edit list, and
wherein the first information is left intact.
2. The information processing apparatus according to claim 1,
wherein the first linking information contains identification information of the first information; and
the second linking information contains linking information that links identification information of the second information to the identification information of the first information.
3. The information processing apparatus according to claim 2, further comprising:
storage means for storing the linking information generated by the generating means;
first acquisition means for acquiring the identification information of the first information; and
supplying means for extracting the identification information of the second information from the linking information stored in the storage means, based on the identification information of the first information acquired by the first acquisition means, and supplying the identification information of the second information.
4. The information processing apparatus according to claim 3, further comprising:
second acquisition means for acquiring the linking information; and
updating means for updating the linking information stored in the storage means using the linking information acquired by the second acquisition means.
5. The information processing apparatus according to claim 1, wherein the second information contains edit information containing an edit content of material data forming the content data, and wherein the first information contains the material data, prior to editing, to be edited in accordance with the edit information.
6. An information processing method of an information processing apparatus for processing first information and second information, each information generated in a production of content data and containing information relating to the content data, the information processing method comprising:
a step of adding, to the second information, first linking information linking the first information;
a step of adding, to the second information, identification information of material data to be edited; and
a step of generating second linking information that links the second information to the first information,
wherein the first information comprises unedited material data prior to editing;
generating means for generating second information comprising a composition table in response to input from a user,
wherein the composition table serves as a plan for editing the first information and the composition table is linked to the first information and the composition table identifies an in point and an out point of an editing process in the first information,
wherein an edit list is generated based on the composition table, comprising an edit description of the editing process and is linked to the first information,
wherein the composition table is acquired based on identification information of the composition table added to the edit list, and
wherein the first information is left intact.
7. A program stored on a removable computer recording medium that for causing a computer to perform an information processing for processing first information and second information, each information generated in a production of content data and containing information relating to the content data, the program comprising:
a step of adding, to the second information, first linking information linking the first information;
a step of adding, to the second information, identification information of material data to be edited; and
a step of generating second linking information that links the second information to the first information,
wherein the first information comprises unedited material data prior to editing;
generating means for generating second information comprising a composition table in response to input from a user,
wherein the composition table serves as a plan for editing the first information and the composition table is linked to the first information and the composition table identifies an in point and an out point of an editing process in the first information,
wherein an edit list is generated based on the composition table, comprising an edit description of the editing process and is linked to the first information,
wherein the composition table is acquired based on identification information of the composition table added to the edit list, and
wherein the first information is left intact.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A method to search for a query image, comprising
detecting local invariant features and local descriptors;
retrieving best matching images by incorporating one or more contexts in matching quantized local descriptors with a vocabulary tree; and
reordering retrieved images with results from the vocabulary tree quantization.
2. The method of claim 1, comprising providing an image specific weighting of local features to reflect the local feature discriminative power in different images.
3. The method of claim 1, comprising matching local spatial contexts of a feature, including density of neighbor’s features, mean scales and orientation differences.
4. The method of claim 1, comprising reusing local feature quantization provided by the vocabulary tree and contexts to perform a fast re-ranking for top retrieved images.
5. The method of claim 1, comprising generating inverted index files for the vocabulary tree.
6. The method of claim 5, comprising training the vocabulary tree offline for local invariant descriptors by hierarchical K-means clustering.
7. The method of claim 5, comprising indexing database images to tree nodes using the inverted index files.
8. The method of claim 1, wherein the vocabulary tree comprises inverted index files, comprising accumulating a similarity score of local features and tree nodes (visual words) vote for an image and providing images with highest similarity scores as retrieval results.
9. The method of claim 1, comprising performing re-ranking to select a subset of local descriptors for SIFT feature matching.
10. The method of claim 9, comprising adding node weights of matched SIFT features in an intersection of two sub graphs specified by neighborhood relations to a matching score to re-order the top candidates
11. The method of claim 1, comprising measuring similarity of local descriptors through image specific descriptor weighting.
12. The method of claim 11, comprising v, where weight wiq is defined based on the node counts along the quantization path of xi , comprising determining
w
i
q
=
\u2211
v
\u2208
T
\ue8a0
(
x
i
)
\ue89e
\u03c9
\ue8a0
(
v
)
\u2211
v
\u2208
T
\ue8a0
(
x
i
)
\ue89e
\u03c9
\ue8a0
(
v
)
\xd7
n
q
\ue8a0
(
v
)
,
(
6
)
where \u03c9(v) is a weighting coefficient set to id\u0192(v) empirically, where weight wiq depends on the descriptor only, and is shared for all nodes v along the path T(xi) and where nq(v) represents a number of descriptors in image q that are quantized to v.
13. The method of claim 1, comprising measuring similarity of local descriptors spatial context statistics.
14. The method of claim 13, comprising builds two graphs from matched {x\u2032i} and {y\u2032j} where x\u2032i links to x\u2033i which is in a spatial neighborhood C(x\u2032i), where C(\u0192) denotes a neighborhood of one feature given by a disc (u,R).
15. The method of claim 14, comprising determining an intersection of the two graphs and adding a weighted id\u0192(vl\u2032,h\u2032) to a matching score sim(q,dm) to re-order top returned images.
16. The method of claim 14, comprising determining a final similarity score of two images as
sim
_
\ue8a0
(
q
,
d
m
)
\ue89e
=
.
\ue89e
sim
\ue8a0
(
q
,
d
m
)
+
\u2211
{
x
i
\u2032
}
\ue89e
\u03b1
\ue8a0
(
x
i
\u2032
)
\ue89e
idf
(
v
l
\u2032
,
h
\u2032
)
,
where
\u03b1
\ue8a0
(
x
i
\u2032
)
=
\uf603
{
x
i
\u2033
|
x
i
\u2033
\u2208
C
\ue8a0
(
x
i
\u2032
)
\ue89e
\ue89e
and
\ue89e
\ue89e
y
i
\u2033
\u2208
C
\ue8a0
(
y
i
\u2032
)
}
\uf604
\uf603
C
\ue8a0
(
x
i
\u2032
)
\uf604
and x\u2033i matches to y\u2033i, the ratio of common neighbors of x\u2032i in the query and its matched feature y\u2032i in the database image.
17. A system to search for a query image, comprising
means for detecting local invariant features and local descriptors;
means for retrieving best matching images by incorporating one or more contexts in matching quantized local descriptors with a vocabulary tree; and
means for reordering retrieved images with results from the vocabulary tree quantization.
18. The system of claim 17, comprising means for providing an image specific weighting of local features to reflect the local feature discriminative power in different images.
19. The system of claim 17, comprising means for matching local spatial contexts of a feature, including density of neighbor’s features, mean scales and orientation differences.
20. The system of claim 1, comprising means for reusing local feature quantization provided by the vocabulary tree and contexts to perform a fast re-ranking for top retrieved images.