XRCE at ImageCLEF 07

1
XRCE at ImageCLEF 07

• Stephane Clinchant, Jean-Michel Renders and
  Gabriela Csurka
• Xerox Research Centre Europe
• France

2
Outline

• Problem statement
• Image Similarity
• Text Similarity
• Fusion between text and image
• Cross-Media Similarities
• Experimental results
• Conclusion

3
Problem Statement

• Problem
• Retrieve relevant images from a given cross-media
  database (images with text) given a set of query
  images and a query text
• Proposed solutions
• Rank the images in the database based on image
  similarity (1), text similarity (2) and
  cross-media similarities (3)

4
Image Similarity

• The goal is to define an image similarity measure
  that is able to best reflect a semantic
  similarity of the images.
• E.g.
• sim( ,
  ) gt sim( , )
• Our proposed solution (detailed in next slides)
  is to
• consider both local color and local texture
  features
• build a generative model (GMM) in the low level
  feature space
• represent the image based on Fisher Kernel
  Principles
• define a similarity measure between Fisher Vectors

5
Fisher Vector

• Given a generative model with parameters ? (GMM)
• the gradient vector
• normalized by the Fisher information matrix
• leads to a unique model-dependent
  representation of the image, called Fisher Vector
• As similarity between Fisher vectors the L1-norm
  was used

Fisher Kernels on Visual Vocabularies for Image
Categorization, F. Perronnin and C. Dance, CVPR
2007.
6
Text similarity

• The text is first pre-processed including
• Tokenization, lemmatization, word decompounding
  and stop-word removal
• The text is modeled by a multinomial language
  model and smoothed via Jelinek-Mercer method
• where pML(w ?d ) ? (w, d) and pML(w ?C ) ?
  ?d(w,d)
• The textual similarity between two documents is
  defined by the cross-entropy function

7
Enriching the text using external corpus

• Reason the texts related to the images in the
  corpus are poor (title only).
• How each text in the corpus was enriched as
  follows
• For each terms in the document we add related
  terms based on their clustered usage analysis an
  external corpus
• The external corpus was the Flickr image database
  
• The relationship between terms was based on the
  frequency of their co-occurrence as tags for
  the same image in Flickr (see top 5 ex. below)

8
Fusion between image and text

• Early fusion
• Simple concatenation of image and text features
  (e.g. bag-of-words and bag-of-visual-words)
• Estimating their co-occurences or joint
  probabilities (Mori et al, Vinokourov et al,
  Duygulu et al, Blei et al, Jeon et al, etc )
• Late fusion
• Simply combining the scores of mono-media
  searches (Maillot et al, Clinchant et al)
• Intermediate level fusion
• Relevance models (Jeon et al )
• Trans-media (or intermedia) feedback (Maillot et
  al, Chang et al)

9
Intermediate level fusion

• Compute mono-media similarities between an
  aggregate of objects coming from a first
  retrieval step and a multimodal object .
• Use the duality of data to switch media during
  feedback process

Pseudo Feedback Top N ranked images based on
image similarity
Final rank Re-ranked documents based on textual
similarity

Aggregate textual information

10
Aggregate information from pseudo-feedback

• Aim
• Compute similarities between an aggregate of
  objects Nimg(q) corresponding to a first
  retrieval for query q and a new multimodal object
  u in the Corpus
• Where Nimg(q)T(I1), T(I2) T(IN) , T(Ik) is
  the textual part of the kth image Ik in the
  (pseudo)-feedback group based on image similarity
• Possible solutions
• Direct Concatenation Aggregate (concatenate)
  T(Ik), k1,N to form a single object and compute
  text similarity between it and T(u).
• Trans-media document re-ranking Aggregate all
  similarity measures between couple of objects .
• Complementary (or Inter-media) Feedback Use a
  pseudo feedback algorithm to extract relevant
  features of Nimg(q) and use them to compute the
  similarity with T(u).

11
Trans-media document re-ranking

• We define the following similarity measure
  between an aggregate of objects Nimg and a
  multimodal object u
• Notes
• This approach can be seen as a document
  re-ranking method instead of a query expansion
  mechanism.
• The values simTXT(T(u),T(v)) can be pre-computed
  offline if the corpus is of reasonable size.
• By duality, we can inverse the role of images and
  text

12
Complementary Feedback

• We derive a LM (?F) for the relevance concept
  from the text set FNimg(q)
• ?F is assumed to be multinomial (peaked at
  relevant terms) estimated by EM from
• where P(w?C) is word probability built upon the
  Corpus, and ? (0.5) a fixed parameter.
• The similarities between Nimg and T(u) is given
  by the cross-entropy similarity
• between ?F and T(u) or we can first interpolate
  ?F with the query text
• Notes
• ? (0.5 in our exp) can be seen as a mixing
  weight between image and text
• Unlike, trans-media re-ranking method, it needs a
  second retrieval step.
• We can inverse the role of images and text if we
  use Rocchios method instead of (1).

A Study of smoothing methods for Language Models
applied to Information Retrieval, Zhai and
Lafferty, SIGIR 2001.
13
XRCEs ImageCLEF Runs

• LM language model with cross entropy
• FVL1 Fisher Vector with L1 norm
• FLR - text enriched by Flicker tags

• TR Transmedia Reranking
• CF Complementary Feedback
• Ri Run I
• QT Query Translation

14
Conclusion

• Our image similarity measure (L1 norm on Ficher
  Vectors) seems to be quite suitable for CBIR.
• It was the second best Visual Only system and
  unlike the first system it does not used any
  query expansion (nor feedback)
• Combining it with text similarity within an
  intermediate level fusion allowed for a
  significant improvement.
• Mixing the modalities increased the performance
  of about 50 (relative) over mono-media (pure
  text or pure image) systems .
• Three out of six proposed cross-media systems
  were the best three Automatic Mixed Runs .
• The system well performed even when the query and
  the Corpus were in different languages (English
  versus German).

15
Thank you for your attention!