Term Frequency in CVPR2017 and CVPR2018 Paper Titles.
====================================================
cvpr_2017_titles : 783
cvpr_2018_titles : 979
====================================================
sort by 'sum', ascending: False
2017 2018 diff sum 2017_norm 2018_norm norm_diff
for 305.0 384.0 79.0 689.0 0.047068 0.048102 0.001034
learning 141.0 216.0 75.0 357.0 0.021759 0.027057 0.005298
and 159.0 189.0 30.0 348.0 0.024537 0.023675 -0.000862
with 120.0 141.0 21.0 261.0 0.018519 0.017663 -0.000856
deep 126.0 122.0 -4.0 248.0 0.019444 0.015282 -0.004162
a 105.0 131.0 26.0 236.0 0.016204 0.016410 0.000206
networks 102.0 112.0 10.0 214.0 0.015741 0.014030 -0.001711
of 93.0 115.0 22.0 208.0 0.014352 0.014406 0.000054
image 92.0 107.0 15.0 199.0 0.014198 0.013403 -0.000794
in 85.0 92.0 7.0 177.0 0.013117 0.011524 -0.001593
network 66.0 95.0 29.0 161.0 0.010185 0.011900 0.001715
from 63.0 80.0 17.0 143.0 0.009722 0.010021 0.000299
3d 57.0 79.0 22.0 136.0 0.008796 0.009896 0.001100
object 52.0 72.0 20.0 124.0 0.008025 0.009019 0.000994
the 62.0 62.0 0.0 124.0 0.009568 0.007767 -0.001801
detection 54.0 69.0 15.0 123.0 0.008333 0.008643 0.000310
to 52.0 67.0 15.0 119.0 0.008025 0.008393 0.000368
neural 57.0 57.0 0.0 114.0 0.008796 0.007140 -0.001656
visual 51.0 62.0 11.0 113.0 0.007870 0.007767 -0.000104
using 56.0 52.0 -4.0 108.0 0.008642 0.006514 -0.002128
====================================================
sort by 'diff', ascending: False
2017 2018 diff sum 2017_norm 2018_norm norm_diff
for 305.0 384.0 79.0 689.0 0.047068 0.048102 0.001034
learning 141.0 216.0 75.0 357.0 0.021759 0.027057 0.005298
adversarial 16.0 61.0 45.0 77.0 0.002469 0.007641 0.005172
and 159.0 189.0 30.0 348.0 0.024537 0.023675 -0.000862
network 66.0 95.0 29.0 161.0 0.010185 0.011900 0.001715
video 39.0 67.0 28.0 106.0 0.006019 0.008393 0.002374
a 105.0 131.0 26.0 236.0 0.016204 0.016410 0.000206
of 93.0 115.0 22.0 208.0 0.014352 0.014406 0.000054
by 28.0 50.0 22.0 78.0 0.004321 0.006263 0.001942
3d 57.0 79.0 22.0 136.0 0.008796 0.009896 0.001100
with 120.0 141.0 21.0 261.0 0.018519 0.017663 -0.000856
estimation 34.0 55.0 21.0 89.0 0.005247 0.006890 0.001643
object 52.0 72.0 20.0 124.0 0.008025 0.009019 0.000994
generative 17.0 35.0 18.0 52.0 0.002623 0.004384 0.001761
attention 12.0 30.0 18.0 42.0 0.001852 0.003758 0.001906
feature 16.0 34.0 18.0 50.0 0.002469 0.004259 0.001790
reidentification 13.0 30.0 17.0 43.0 0.002006 0.003758 0.001752
from 63.0 80.0 17.0 143.0 0.009722 0.010021 0.000299
towards 2.0 17.0 15.0 19.0 0.000309 0.002130 0.001821
detection 54.0 69.0 15.0 123.0 0.008333 0.008643 0.000310
====================================================
sort by 'diff', ascending: True
2017 2018 diff sum 2017_norm 2018_norm norm_diff
classification 28.0 16.0 -12.0 44.0 0.004321 0.002004 -0.002317
binary 13.0 1.0 -12.0 14.0 0.002006 0.000125 -0.001881
objects 16.0 6.0 -10.0 22.0 0.002469 0.000752 -0.001718
flow 19.0 10.0 -9.0 29.0 0.002932 0.001253 -0.001679
recognition 57.0 48.0 -9.0 105.0 0.008796 0.006013 -0.002784
joint 19.0 11.0 -8.0 30.0 0.002932 0.001378 -0.001554
adaptive 13.0 5.0 -8.0 18.0 0.002006 0.000626 -0.001380
matrix 10.0 2.0 -8.0 12.0 0.001543 0.000251 -0.001293
search 10.0 3.0 -7.0 13.0 0.001543 0.000376 -0.001167
bayesian 7.0 0.0 -7.0 7.0 0.001080 0.000000 -0.001080
convolutional 46.0 39.0 -7.0 85.0 0.007099 0.004885 -0.002213
spatiotemporal 13.0 6.0 -7.0 19.0 0.002006 0.000752 -0.001255
fully 11.0 4.0 -7.0 15.0 0.001698 0.000501 -0.001196
multimodal 13.0 6.0 -7.0 19.0 0.002006 0.000752 -0.001255
temporal 16.0 10.0 -6.0 26.0 0.002469 0.001253 -0.001216
multiperson 6.0 1.0 -5.0 7.0 0.000926 0.000125 -0.000801
representation 18.0 13.0 -5.0 31.0 0.002778 0.001628 -0.001149
residual 13.0 8.0 -5.0 21.0 0.002006 0.001002 -0.001004
rank 7.0 2.0 -5.0 9.0 0.001080 0.000251 -0.000830
models 20.0 15.0 -5.0 35.0 0.003086 0.001879 -0.001207
====================================================
sort by 'norm_diff', ascending: False
2017 2018 diff sum 2017_norm 2018_norm norm_diff
learning 141.0 216.0 75.0 357.0 0.021759 0.027057 0.005298
adversarial 16.0 61.0 45.0 77.0 0.002469 0.007641 0.005172
video 39.0 67.0 28.0 106.0 0.006019 0.008393 0.002374
by 28.0 50.0 22.0 78.0 0.004321 0.006263 0.001942
attention 12.0 30.0 18.0 42.0 0.001852 0.003758 0.001906
towards 2.0 17.0 15.0 19.0 0.000309 0.002130 0.001821
feature 16.0 34.0 18.0 50.0 0.002469 0.004259 0.001790
generative 17.0 35.0 18.0 52.0 0.002623 0.004384 0.001761
reidentification 13.0 30.0 17.0 43.0 0.002006 0.003758 0.001752
network 66.0 95.0 29.0 161.0 0.010185 0.011900 0.001715
estimation 34.0 55.0 21.0 89.0 0.005247 0.006890 0.001643
transfer 12.0 26.0 14.0 38.0 0.001852 0.003257 0.001405
generation 9.0 22.0 13.0 31.0 0.001389 0.002756 0.001367
adaptation 10.0 23.0 13.0 33.0 0.001543 0.002881 0.001338
answering 8.0 20.0 12.0 28.0 0.001235 0.002505 0.001271
question 9.0 21.0 12.0 30.0 0.001389 0.002631 0.001242
inference 6.0 17.0 11.0 23.0 0.000926 0.002130 0.001204
person 19.0 33.0 14.0 52.0 0.002932 0.004134 0.001202
unsupervised 17.0 30.0 13.0 47.0 0.002623 0.003758 0.001135
pose 26.0 41.0 15.0 67.0 0.004012 0.005136 0.001124
====================================================
sort by 'norm_diff', ascending: True
2017 2018 diff sum 2017_norm 2018_norm norm_diff
deep 126.0 122.0 -4.0 248.0 0.019444 0.015282 -0.004162
recognition 57.0 48.0 -9.0 105.0 0.008796 0.006013 -0.002784
classification 28.0 16.0 -12.0 44.0 0.004321 0.002004 -0.002317
convolutional 46.0 39.0 -7.0 85.0 0.007099 0.004885 -0.002213
using 56.0 52.0 -4.0 108.0 0.008642 0.006514 -0.002128
binary 13.0 1.0 -12.0 14.0 0.002006 0.000125 -0.001881
semantic 47.0 43.0 -4.0 90.0 0.007253 0.005386 -0.001867
the 62.0 62.0 0.0 124.0 0.009568 0.007767 -0.001801
objects 16.0 6.0 -10.0 22.0 0.002469 0.000752 -0.001718
networks 102.0 112.0 10.0 214.0 0.015741 0.014030 -0.001711
flow 19.0 10.0 -9.0 29.0 0.002932 0.001253 -0.001679
neural 57.0 57.0 0.0 114.0 0.008796 0.007140 -0.001656
in 85.0 92.0 7.0 177.0 0.013117 0.011524 -0.001593
joint 19.0 11.0 -8.0 30.0 0.002932 0.001378 -0.001554
adaptive 13.0 5.0 -8.0 18.0 0.002006 0.000626 -0.001380
action 32.0 29.0 -3.0 61.0 0.004938 0.003633 -0.001306
matrix 10.0 2.0 -8.0 12.0 0.001543 0.000251 -0.001293
spatiotemporal 13.0 6.0 -7.0 19.0 0.002006 0.000752 -0.001255
multimodal 13.0 6.0 -7.0 19.0 0.002006 0.000752 -0.001255
temporal 16.0 10.0 -6.0 26.0 0.002469 0.001253 -0.001216